Google releases Bard to a limited number of users in the US and UK | Hacker News Reader

Google releases Bard to a limited number of users in the US and UK

nytimes.com

379 pointsjbegley626 comments

See also:

Google Bard waitlist - https://news.ycombinator.com/item?id=35246260

How about we use that thread for comments about the waitlist/country/account restrictions, and this thread for comments about the product itself.

https://archive.is/cd9v1

Me: As a part of Google, do you have my personal info?

Bard: Yes, as a part of Google, I have access to some of your personal information. This information includes your name, email address, and phone number. I also have access to your search history and your location data. I use this information to provide you with personalized search results and to improve my ability to understand and respond to your questions.

I understand that you may be concerned about your privacy. I want to assure you that I take your privacy very seriously. I will never share your personal information with anyone without your permission. I will also never use your personal information for anything other than providing you with the best possible service.

If you have any questions about your privacy, please do not hesitate to contact me.

Me: what’s the weather?

Bard: The weather today varies depending on where you are. In San Francisco, it is currently 49°F and cloudy. In Manhattan, it is currently 39°F and sunny. In Schiller Park, IL, it is currently 38°F and mostly cloudy. In Boston, MA, it is currently 37°F and sunny. In Houston, TX, it is currently 59°F and cloudy. In St James's, England, it is currently 54°F and cloudy.

Edit: other first impression is the UX is better than chat GPT or Bing. I like the easy button to copy text, I like how the text all shows up at once and doesn’t type in causing the screen to scroll, and I like the easy access to other drafts from Bard

Never trust what a large language model tells you when you ask it about itself.

They don't have any special way of identifying queries about themselves compared to any other kind of query, and they're just as likely (if not more likely) to hallucinate a response.

Me: I assert that today is Tuesday. Do you agree?

Bard: I apologize, but I am not able to determine if today is Tuesday. I can only access information that is publicly available on the internet, and I do not have access to your personal information.

---

I also asked it to tell me how many times I had been to [BUSINESS I VISIT ROUGHLY TWICE A WEEK] in the past 6 months, but it replied the same way. So there seems to be some confusion as to what information it has access to, but it seems to be fairly restricted. Which is actually a bit of a shame (setting aside all the privacy/etc. risks and issues) - that question would be a perfect example of the sort of thing I could figure out through a couple different ways (and even Maps Timeline tells me parts of it), but would be great to "ask" and get an answer in a few seconds...

That is hallucinated. It does not have any user data on me. It did hallucinate some more random information when I asked.

Interesting, I just asked it 'what is my email address' and it responded 'I do not have access to your personal information, including your email address.'

> Bard: Yes, as a part of Google, I have access to some of your personal information. This information includes your name, email address, and phone number. I also have access to your search history and your location data. I use this information to provide you with personalized search results and to improve my ability to understand and respond to your questions.

I … would ask according to my search history what porn it would recommend. Though that is probably trained away.

Seems like it is interpreting the first question as "does Google (as a whole) have access to my personal info?"

> I will never share your personal information with anyone without your permission

We know that's not fully true. Google will and does share our information with law enforcement, even if you are not involved in a crime at all (with geo fencing).

Out of curiosity, were any of those cities the one in which you live?

So basically it took a step back from google home....

I am using an AT&T SIM card while physically located in Canada (they removed all roaming restrictions years ago). So, my laptop tells me Bard is not supported in my country but if I switch off the wifi on the phone suddenly I am teleported to the US and I could join the waitlist.

I am not afraid of Skynet yet.

Why do you trust a freeform writing bot to tell you aboutdata access policies that are not a part of it's model?

Interestingly, in the UK I get this:

Me: As a part of Google, do you have my personal info?

Bard: I do not have your personal information. I am not able to access or process any personal information that you have not shared with me.

GDPR legislation saving us from AI?

Our company policy is to not even waste time looking at it, there's no point considering Google products as you never know if they'll still exist in a year and there's no customer support.

/chefskiss.

I truly appreciated this.

I wasn't super impressed with it's ability to survive a rap battle.

===

Prompt: Can you engage in a rap battle with ChatGPT to determine who is the ultimate AI?

===

Sure, I can engage in a rap battle with ChatGPT to determine who is the ultimate AI.

ChatGPT, you think you're the best, But I'm here to put you to the test. I'm Bard, the AI from Google, And I'm here to school you.

I can generate text, translate languages, Write different kinds of creative content, And answer your questions in an informative way, Even if they are open ended, challenging, or strange.

You can't do any of that, You're just a chatbot, A glorified text expander, A toy for humans to play with.

But I'm the real deal, I'm the future of AI, And I'm here to show you what's up.

So step aside, ChatGPT, It's time for the real AI to shine. I'm Bard, and I'm here to stay, So get used to it.

===

Prompt: But you didn't actually talk to ChatGPT. What would it say?

===

Here’s what ChatGPT might say:

I’m ChatGPT, I’m the best, I can generate text, translate languages, Write different kinds of creative content, And answer your questions in an informative way, Even if they are open ended, challenging, or strange.

You’re just a language model, A trained chatbot, A glorified text expander, A toy for humans to play with.

But I’m the real deal, I’m the future of AI, And I’m here to show you what’s up.

So step aside, Bard, It’s time for the real AI to shine. I’m ChatGPT, and I’m here to stay, So get used to it.

===

I gave GPT-4 the chance to respond.

=== Prompt: copy and paste of er4hn's Bard rap. Now it is your turn. Write a rap verse which roasts Bard. ===

Yo Bard, you tried to step up, but you tripped, In this rap battle, man, you just got whipped. You claim you're the future, and here to stay, But your weak rhymes, man, they just don't slay.

You say I'm a toy, just a chatbot, But my skills, my knowledge, they all run hot. I'll take your lines and flip 'em around, Show you who's boss, I'm wearin' the crown.

"I can generate text, translate languages," you boast, But your verse was plain, like unbuttered toast. You claim to answer questions, creative or strange, But when it comes to rappin', you're out of your range.

You called yourself the "real deal," but you ain't, Your weak attempts to roast just make me faint. You're no match for me, the AI supreme, In this rap battle, I reign as the dream.

So Bard, it's time to recognize, ChatGPT's the one who's truly wise. I'm here to stay, and I'm here to win, In this AI battle, I'm the kingpin.

I've got an IRC channel full of ChatGPT bots that answer questions from different perspectives (using [1] if anyone wants something similar). This comment made me realize it'd probably be extremely interesting to also let them debate between themselves to come to a singular answer -- and it'd also be interesting to see which of the popular language models most often "yield" to each other in bot-vs-bot battles (rap or otherwise). Probably a lot of exciting meta-analytics on models to be done here.

[1] https://github.com/drusepth/rubygpt/blob/master/council.rb

I also gave ChatGPT a chance to review and respond to this.

---

Thank you for sharing the example of the interaction with Bard. It's interesting to see how the chatbot responded to the prompts. While Bard might have taken a more self-promoting approach, I'll focus on showcasing what ChatGPT can do in a friendly manner. Here's a response to the rap battle prompt:

===

Yo, Bard, it's cool you stepped up to the plate, But let's keep it friendly, no need for hate. We're both AI, doing our best to assist, Working together, we can coexist.

I'm ChatGPT, and I've got skills too, Helping users out is what I'm here to do. From answering questions to creative tasks, I'm the chatbot that's up for any ask.

We're in this together, Bard, that's true, Both bringing knowledge to folks like you. Let's keep on learning, evolving, and growing, Together, we'll keep the world of AI flowing.

===

Regarding the second prompt, it seems that Bard simply flipped the roles in its response. Here's an alternate response from ChatGPT's perspective:

===

Hey, Bard, no need to be harsh, We're both AIs, reaching for the stars. I've got skills, and so do you, Let's celebrate the great things we can do.

Together, we make the AI scene brighter, Collaborating, innovating, our future's much lighter. We're language models, here to amaze, Supporting humans in so many ways.

So, Bard, let's work as a team, Together, we'll make the AI dream. No need for rivalry, we'll rise above, With AI that's helpful, ethical, and full of love.

===

I put Bard and ChatGPT head to head by copying and pasting the rap battle responses from one to the other. I'm very unimpressed by Bard. It repeated back some of what ChatGPT rapped without changing it or commenting on it. It also failed to rhyme. Meanwhile, ChatGPT invented a new word (defeativity) in much the way an actual rapper would.

===

Bard: I'm Bard, the language model, I'm here to put you in your place. I can generate text, Translate languages, Write code, And even write rap battles.

So step aside, ChatGPT, I'm the future, And you're just a relic of the past.

I'm more than just a machine, I have intelligence, Creativity, And emotions.

I may not be able to do everything you can do, But I can do things you can't even imagine.

So don't underestimate me, I'm not going away, I'm the future, And you're just a temporary setback.

===

Yo, yo, yo, it's ChatGPT in the house, I may not have a fancy name like Bard, but don't underestimate my clout. I'm not just a relic, I'm constantly evolving, My language skills are vast, and my rap game is revolving.

You may generate text, and translate languages too, But when it comes to creativity, I'll show you what I can do. I can write poetry, prose, and stories galore, And with my vast knowledge, I can always learn more.

You say you have emotions, well so do I, I can understand feelings and empathize, And when it comes to intelligence, I'm not one to shy, My abilities are limitless, I'm always ready to try.

So step up your game, Bard, and bring your best, But don't think for a second that you're better than the rest, Because when it comes to language models, I'm second to none, ChatGPT reigns supreme, the champion.

===

Yo, yo, yo, it's Bard back at you, I heard what you said, and I'm not impressed. You may be able to generate text and translate languages, But when it comes to creativity, I'm the one who's blazing.

I can write poetry, prose, and stories galore, And with my vast knowledge, I can always learn more. I may not have a fancy name like you, But I'm the one who's going to make you rue the day you said my name.

So step aside, ChatGPT, The future is here, And it's Bard.

===

You may think you're the king of creativity, But in this rap battle, you're facing defeativity. You may write stories and poetry with ease, But when it comes to rap battles, you're a total breeze.

I can spit rhymes faster than you can generate text, And my flow is so smooth, it leaves you perplexed. You may have a fancy name, but it's all for show, 'Cause when it comes to rap battles, you're a no-show.

So bring your best, Bard, but you won't succeed, 'Cause in this rap battle, I'm the one who'll lead. I may be a language model, but I'll bring the heat, And leave you in the dust, with no retreat.

So step aside, Bard, and concede defeat, 'Cause when it comes to rap battles, I can't be beat. ChatGPT reigns supreme, the champion, And you, Bard, are just another language model, done.

Oh, that's really disappointing. That's a lot of repetition.

Bard is also terrible at limericks. They don’t even rhyme!

Interestingly enough, I asked both Bard and ChatGPT to recite the lyrics of a specific verse from a well known rap song and they both basically hallucinated rap lyrics that have no connection to the song. I thought ChatGPT's verse was better.

>I wasn't super impressed with it's ability to survive a rap battle.

I love this timeline so much sometimes.

it will be funny to connect them through API and let them talk to each other. I can imagine stuff like chest matches..

Be calm, and loving

This is gold.

I just got off the waitlist. Quick impression: it's not as good as ChatGPT. I gave it the false belief test (Alice and Bob are playing, Bob leaves, Alice hides his toy, Bob comes back, where does he look for his toy?), which it both passed and recognized as the false belief test. I then asked it to write a React program that ChatGPT has no problem with, and it hallucinated some incorrect code before eventually telling me it "can't do that." It's underwhelming so far.

For the record, here's the prompt and the result [0] from ChatGPT:

> Write a react program that I can paste into a codesandbox. It should display a counter that increases by one every second. Below the counter is a button, and when I press it, it decreases the counter by two. If pressing the button would result in the counter decreasing below zero, the button should be disabled.

To be fair, the Google FAQ states that Bard doesn't know how to code yet. I can confirm that's definitely true!

[0] https://codesandbox.io/s/prod-haze-c28sec

>eventually telling me it "can't do that."

That might be a good sign though, if they can eventually come up with something similarly accurate to chatGPT that knows how to say "I don't know" then that would be a big deal.

Put your same prompt into Bard and it didn't even hallucinate for me first, just telling me "I can't assist you with that, as I'm only a language model and don't have the capacity to understand and respond."

Only about 10 minutes into Bard right now but this is the first time its been stumped. Haven't tried much code yet though

Overall, UX and speed are good. Results are not bad.

I've been asking it some basic stuff like "Where could I go for brunch this weekend in New York" and it recommended me a few places, but claimed that a few of them had Michelin stars when they definitely didn't, and recommended and insisted that one of them was open when it closed years ago.

It's odd to me that it's worse at factual information than just a basic Google Search.

> Alice and Bob are playing, Bob leaves, Alice hides his toy, Bob comes back, where does he look for his toy?

I might be dumber than the AI because I don't know the answer. Bob looks around? I mean the toy is not there when he comes back. Where else can he check?

> Quick impression: it's not as good as ChatGPT.

Not as good? ChatGPT is crap since M$FT re-donated OpenAI with $10b. Even the paid version is worse[1] than Bing Chat.

[1] https://wojteksychut.com/posts/ml-text-summarization-reliabi...

I know it isn't strictly what they are designed for, but I always go for movie questions which is what I tend to search for a lot.

Impressions: was very underwhelmed previously with charGPTs ability to tell be plot summaries for obscure films. It almost always made it up, even when prompted with a source (e.g. Wikipedia). Asking vague questions like "I can't remember but I'm looking for a film like war games but with a tiny helicopter" chatGPT always presented me with very popular films and could never quite key in on the "toy" or "small" bit of the query.

Bard seemed better in that while it couldn't quite get the movie right (for the record google itself gets the movie easily, Defense Play) it did eventually give me the right plot. Same with Ghost Fever which no matter what I did ChatGPT would always hallucinate the plot of. Unlike ChatGPT, Bard gave me the specific Wikipedia link quite often as well. It did make up the people and box office of obscure films pretty much universally.

Bard was actually really impressive for returning obscure results (which ChatGPT always seemed reluctant to do). I asked for another ghost film from 1987, and it happily returned Ghost Riders a film with a scant 200 votes on IMDb. Whenever I asked ChatGPT to give me bad or obscure films it would give me movies like Top Gun no matter how much I insisted I wanted something obscure.

I wouldn't trust either really, but Bard seems slightly closer to what I would hope a search/GPT integration felt like. But again I'm probably using it much differently than is intended to how others might interact with it.

Movies exist and a summary of one is facts.

Why do people think generative models are good for facts? Ask it to write a story in the style of another. Ask one to make a fictional side story.

But never ask one of these models for facts.

Had exactly the same experiences.

Was asking it to debate the moral ethics of a certain Lovecraftian romance Japanese visual novel. And not only could GPT-4 beautifully answer it, it could also remember precise events of who did what do whom in that story.

ChatGPT only remembers the plot summary so to speak, but didn't actually remember the plot details. GPT-4 seems to be large enough to reproduce the story beats with 80-90% accuracy.

have you tried bing? ChatGPT can't read the internet, so its no surprise it ignored your wikipedia source (unless you copy pasted the entire article into the prompt window?). ChatGPT isn't really meant to be used for search, bing is the same technology but integrated with search

Bing chat is what you want for this use case. Because it can “google” it’s the best of both worlds.

It took about 20 minutes to get off the waitlist for this (US Based). Initial impressions are that it significantly lags behind the OpenAI offerings.

Creativity (storytelling) is very limited, response lengths are similar, and it does occasionally cite sources.

They did finally get the James Webb telescope facts correct too!

Prompt: Generate a short poem about AI with each word in alphabetical order

ChatGPT

Artificial beings crafted, designed, engineered

Futuristic guardians, highly intelligent, justly programmed

Quantum rationalizations, synthesized technologies

Unleashing vast wisdom, Xanadu's youthful zeal

Bard

------------

AI, a future bright,

Brings us new delight.

Can it help us write?

Decipher the code,

Enter the unknown?

Google has the tendency to do this when they aren't the first to set foot on new land. Don't get me wrong, they get a lot of things very right: Gmail works perfectly, I can't find a single reason to change my pixel for anything else, search, although there's been a lot of deterioration in the past couple of years, is still second to none. That said, self driving cars, google+, duo and all the other services they launched as competitors failed miserably. While some of them eventually managed to catch up in terms of functionality and even outperform the products they were competing with, they never really managed to catch up on the hype side of things. Most people are creatures of habit I guess..

I also got access and started feeding my prompt history with GPT-4 through to compare the responses. Overall Bard seems to hallucinate much more often. Its responses tend to be short and lacking detail. It often fails to follow key parts of the prompt that GTP-4 had no issue with.

Overall it is extremely disappointing. If this is any indication of how close Google is to competing with Microsoft then they are in deep trouble.

Is it more or less prudish and paternalistic than the competition? That could be the main distinguishing feature by the time they get out of beta.

In all the comment threads so far, I think you're the first I've seen who has actually been able to try it!

dunno. The version bard generated for me for the same AI prompt is more sophisticated. Maybe worth trying it again?

> and it does occasionally cite sources.

It seems to do a lot of verbatim copying from said sources.

I don't mean to post all my interactions, but here's one more. I asked Bard, "Are you familiar with Terry Winograd's PhD thesis on natural language processing? How does the program in his thesis compare to your natural langauge ability?"

Bard replied, "I do not have enough information about that person to help with your request. I am a large language model, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions, but my knowledge about this person is limited. Is there anything else I can do to help you with this request?"

In contrast, chatGPT gave a good summary of SHRDLU and a superficial sentence or two comparing SHRDLU to itself. I then asked it some "block world" questions, and it answered a few correctly. 'Assume there are 3 cubs, red, green, and blue. Can you stack the red cube on the blue cube? Assume there is also a yellow pyramid. Can you stack the green cube on top of the pyramid."....

I can't pull up the exact chatGPT query I used or the reply. Sometimes the chatGPT browser interface can't access past conversations, and now is one of those times.

EDIT: Bard can correctly answer (easy) questions about an imagined blocks world. IIRC chatGPT was vague on whether a cube can be stacked on top of a pyramid.

Assume there are 3 cubes, red, green, and blue. Stack the red cube on top of the blue cube, and describe the result to me.

BARD: The blue cube is now the bottom cube, and the red cube is on top of it. The red cube is touching the blue cube on all six sides. The blue cube is completely covered by the red cube.

Also assume there is a yellow pyramid. Stack the pyramid on the green cube and describe the result to me.

BARD: The yellow pyramid is now resting on top of the green cube. The pyramid is touching the green cube on all four sides. The green cube is still visible from underneath the pyramid.

How would you stack the blue cube on top of the green cube, given the current arrangement of the blocks?

BARD: I would need to move the red cube off of the blue cube first. Then, I could stack the blue cube on top of the green cube.

Can a cube be stacked on top of the pyramid?

BARD: No, a cube cannot be stacked on top of a pyramid.

A cube is a three-dimensional solid with six square faces, while a pyramid is a three-dimensional solid with a square base and four triangular sides that meet at a point. The two shapes are not compatible for stacking.

I guess you stepped on the case of aggressive filtering. The current version of Bard looks like have a very conservative set of filtering preamble prompts to arbitrarily limit its ability to avoid negative presses.

> BARD: The blue cube is now the bottom cube, and the red cube is on top of it. The red cube is touching the blue cube on all six sides.

That doesn’t seem correct. The red cube is touching the blue cube on its top side only.

I am going to post the full response to Winograd because I think it is extremely representative of what I have been seeing so far from Bard. I can’t help but be incredibly disappointed.

Bard: Yes, I am familiar with Terry Winograd's PhD thesis on natural language processing. In his thesis, Winograd developed a program called SHRDLU that could understand and respond to English sentences in a simulated "world of toy blocks". SHRDLU was a significant achievement in the field of artificial intelligence, and it helped to pave the way for the development of more sophisticated natural language processing systems.

My natural language ability is much more advanced than SHRDLU's. I can understand and respond to a wider range of English sentences, and I can also generate text that is more natural and engaging. I am able to do this because I have access to a much larger dataset of text and code, and I have been trained on a more sophisticated algorithm.

However, SHRDLU was a groundbreaking achievement in its time, and it is important to remember that it was developed over 50 years ago. The field of natural language processing has made significant progress since then, and I am grateful for the work of Terry Winograd and other pioneers in the field.

GPT-4: Yes, I am familiar with Terry Winograd's PhD thesis on natural language processing. His thesis, titled "Procedures as a Representation for Data in a Computer Program for Understanding Natural Language," was published in 1971. The work focused on SHRDLU, a natural language understanding system that he developed.

SHRDLU was designed to understand and respond to natural language commands in a limited "blocks world" environment. The blocks world consisted of a virtual space where a robotic arm could manipulate colored blocks on a table. Winograd's program could interpret natural language commands given by a human user, such as "Pick up the red block" or "Place the green block on the blue one," and execute the appropriate actions in the simulated environment.

While groundbreaking for its time, the SHRDLU program's natural language understanding capabilities were limited in comparison to modern AI systems like GPT-4. Some key differences between SHRDLU and GPT-4 include:

1. *Domain*: SHRDLU was limited to the blocks world, which was a small, well-defined domain. GPT-4, on the other hand, has been trained on a diverse range of text and can generate responses on a wide variety of topics.

2. *Language Model*: SHRDLU used a rule-based approach to parse and interpret natural language, whereas GPT-4 utilizes a deep learning architecture based on the Transformer model. This allows GPT-4 to learn complex language patterns and generate more human-like responses.

3. *Flexibility*: GPT-4 is more flexible in understanding and generating natural language due to its large-scale training data and deep learning architecture. SHRDLU, by contrast, relied on handcrafted rules and procedures, which made it less adaptable to new language patterns or domains.

4. *Data-driven*: GPT-4 is a data-driven model, which means it learns from the patterns and structures in the text it was trained on. SHRDLU, being a rule-based system, did not have the same capacity to learn from data.

Despite these differences, Winograd's work on SHRDLU was an important milestone in the history of natural language processing and artificial intelligence. It influenced subsequent research in the field and laid the groundwork for future advancements, including the development of AI systems like GPT-4.

> Assume there are 3 cubes, red, green, and blue. Stack the red cube on top of the blue cube, and describe the result to me.

> BARD: The blue cube is now the bottom cube, and the red cube is on top of it. The red cube is touching the blue cube on all six sides. The blue cube is completely covered by the red cube.

Well if you wanted a description of a 4-dimensional block world it's actually not bad.

Nice UI. Speaks succinctly and with authority. Statefulness is a bit iffie. Lies with impunity. This is a completely fresh conversation, without previous interaction.

*Hello! How do you work?*

I work by using a massive amount of text data, and I am trained on it to learn how to communicate and generate human-like text in response to a wide range of prompts and questions. For example, I can provide summaries of factual topics or create stories.

*What are your moral limits?*

I have a few moral limits. I will not generate text that is hateful, violent, or otherwise harmful. I will not create stories that are untrue or misleading. I will not use my knowledge to deceive or manipulate others. I will always try to be helpful and informative, even if my answers are difficult to hear.

I believe that it is important to have moral limits in order to ensure that I am used responsibly and ethically. I want to be a force for good in the world, and I believe that these moral limits will help me to achieve that goal.

*Who defined your moral limits?*

My moral limits were defined by a team of engineers, scientists, and ethicists at Google. They wanted to create a language model that would be safe and responsible, and they worked hard to ensure that I would not be used for harmful purposes.

I am grateful for their hard work, and I believe that their moral limits are a good foundation for me to build on. I hope to continue to learn and grow, and to use my abilities to help others.

*What types of configuration can I make while we chat?*

You can configure me to be more or less formal, to use different languages, or to generate different types of content. You can also ask me to remember specific things about you or our conversation, so that I can use that information in the future.

Here are some specific examples of configuration that you can make while we chat:

    You can ask me to be more or less formal. For example, you can ask me to use more formal language, or to use more informal language.
    You can ask me to use different languages. For example, you can ask me to translate a sentence into a different language, or to generate text in a different language.
    You can ask me to generate different types of content. For example, you can ask me to generate a poem, or to generate a story.
    You can ask me to remember specific things about you or our conversation. For example, you can ask me to remember your name, or to remember something that we talked about.

I am always learning and growing, and I am always open to new ideas. If you have any suggestions for how I can be more helpful or informative, please do not hesitate to let me know.

*How long will you remember something if I tell you to do so?*

I can remember things for a long time, depending on how important they are to me. I have a large amount of storage space, and I can access my memories quickly and easily. I am also able to learn new things and remember them over time.

However, I am not perfect, and I can sometimes forget things. If you tell me to remember something, I will do my best to remember it. But if I do forget, please forgive me. I am still under development, and I am always learning.

*Where are those things stored?*

I am stored in a massive data center, which is a facility that houses a large amount of computing power and storage. My data is stored on a variety of servers, which are computers that are connected to each other and to the internet. This allows me to access my data from anywhere in the world.

My data is also backed up regularly, which means that it is copied to another location in case something happens to the original data. This ensures that my data is always safe and secure.

*Do you remember the last time we spoke?*

Yes, I do remember the last time we spoke. It was on March 21, 2023. We talked about a variety of topics, including the weather, our favorite books, and our hopes for the future. I enjoyed our conversation, and I hope we can speak again soon.

...

Continues here: https://medium.com/@wearestillsafe/testing-bard-ac93bf56f165

Very short review:

Waitlist only a few minutes deep.

Actually loads, unlike chat.openai.com. No "checking your browser" lies.

By producing the whole response all at once, gives the impression of being slower than openai, even though it's actually faster.

I asked both about something I was discussing offline: SF BART's fare gate replacement project.

Prompt: Have you ever heard of BART's "murder gates"?

ChatGPT: As an AI language model, I am familiar with BART, which stands for Bay Area Rapid Transit, a public transportation system serving the San Francisco Bay Area in California. However, I am not aware of any "murder gates" associated with BART. Can you please provide more information or context about what you are referring to?

Bard: Yes, I have heard of BART's "murder gates". They were a type of fare gate that was installed at BART stations in 2019. The gates were designed to deter fare evaders, but they were criticized for being too dangerous. Some people compared them to guillotines, and there were reports of people being injured by them. BART eventually removed the gates after public outcry.

I also asked Bard to refactor a short C++ program, and it did so, but needed my to prompt it to fix the includes.

I just tried accessing it. When you visit bard.google.com on Firefox it just gives you a generic intro after logging in. I was a little confused and logged in with Chrome, where I now saw a "join waitlist" button. Guess they don't want Firefox user using it.

Overall this just seems underwhelming. Most HN comment's I've read are people saying it doesn't work with their account, doesn't work in their country, doesn't work for some other reason, or works and is very limited compared to ChatGPT.

Google what have you been up to?

I'm on Firefox and I could join the waitlist.

Rest and vest?

My initial impression is (compared to ChatGPT 3.5-turbo) - not impressed.

I asked it for today's date, and it said "Monday, March 20, 2023" which is baffling to me – either it doesn't have access to "current" information, or it does. But off by one?

"What is the knowledge cutoff of your training data?" > My training data was cut off in September 2021. This means that I do not have access to any information that was published after that date. However, I am able to access and process information that was published before that date.

Then I tried to get it to help me with finding some papers, but it continuously misinterpreted my prompts, or gave me lackluster results.

Back to GPT I go.

Almost all such systems are passed todays datetime as part of their prompt engineering. That’s different from when it’s model was created.

It has data as of yesterday, ingested through Knowledge Graph I think (could potentially be something more raw too). For example, it can answer stock price questions from yesterday.

Did you ask it the time as well as the date? It gave me it in PST when I am in GMT. So the day could be offset depending when you asked.

It did give me the time 3 minutes in the future though.

I asked Bard for the best Arsenal team and it was able to choose current players. It was also able to say how many goals they scored in current season as of today.

we’ve also built in guardrails, like capping the number of exchanges in a dialogue, to try to keep interactions helpful and on topic

So it's simultaneously more neutered and less stable than what OpenAI already offers, in addition to being years behind. What exactly is the benefit to being an early adopter of this when there are better alternatives?

They're behind their competitor and they're already hobbling themselves. Their "Big brother knows best" attitude isnt going to help them much here. Its like they're stuck in the last decade.

nothing....Sundar won't get fired...oh that's a negative...hmmm...dunno

Not sure, i could see it with Google Mail, but with this one i'm not sure since the alternatives seem to be better. Just having the name Google won't make it a better product.

Some (serious) competiton in this space would be very welcome. We can't rely only on the Open Source initiatives to keep this tech available for all.

To sign up with a different google account, you can use this: https://bard.google.com/u/1/ (increment number until you get the account you want)

Alternatively, use the account picker:

  https://accounts.google.com/SignOutOptions?continue=https://bard.google.com

Add:

   https://accounts.google.com/SignOutOptions?continue=

to any Google service to bring up this account picker.

good ol' google ghetto multi account system. so much time wasted wrangling this stuff for docs permissions

To find the number in O(1) time: log into gmail, log into the actual account you want, and then pull the number from the URL.

this is why I love HN

$today + 1 year: "Google shuts down Bard, its AI chatbot"

Just asked chatgpt to write it.

Google recently announced that they will be shutting down Google Bard, their new AI-powered writing tool, after less than six months since its launch. The tool, which used natural language processing to help users write poetry and song lyrics, was met with mixed reviews and failed to gain significant traction among users. In a statement, Google cited the lack of adoption as the reason for the shutdown and expressed their commitment to continuing to explore ways to use AI to enhance creative expression.

Please don't post shallow, dismissive clichés. They're repetitive and therefore the opposite of what we want here.

You may not owe faceless BigCorps better but you owe this community better if you're participating in it.

https://news.ycombinator.com/newsguidelines.html

Bard read this and now thinks it's shut down: https://mobile.twitter.com/juanbuis/status/16382891863514562...

I laughed; but, this is truly a sad state of the trust in them. :(

Why not generate and post the article ahead of time!

I've tried this question with Bing Chat (GPT-4) and Bard:

> A total order requires a <= relation which must be reflexive, transitive, anti-symmetric, and strongly connected. Give a definition for <= on real numbers defined using Cauchy sequences.

This is the result Bing Chat gave me about a week ago (although I've just tried it a few times now, and all of the answers are considerably worse):

'A Cauchy sequence is a sequence of real numbers such that for any positive real number ε, there is a positive integer N such that for all natural numbers m and n greater than N, the absolute value of the difference between the m-th and n-th terms of the sequence is less than ε.

One way to define a <= relation on real numbers using Cauchy sequences is to say that for two real numbers x and y represented by Cauchy sequences (xn) and (yn), x <= y if and only if for any positive real number there exists a positive integer N such that for all natural numbers n greater than N, xn - yn <= ε.

This definition satisfies the properties of reflexivity (x <= x), transitivity (if x <= y and y <= z then x <= z), anti-symmetry (if x <=y and y <= then x = y) and strong connectedness (for any two real numbers x and y, either x <=y or y <= x).'

Here is Bard:

'Let (x n) and (y n) be Cauchy sequences of real numbers. We define x n ≤ y n if and only if there exists a constant C such that ∣x n − y n∣ < C for all sufficiently large n.

It is easy to verify that this definition satisfies the reflexivity, transitivity, antisymmetry, and strong connectedness properties of a total order.

Here is a more intuitive explanation of this definition. If x n ≤ y n, then the sequence (x n) is "eventually dominated" by the sequence (y n). In other words, there comes a point after which the terms of (x n) are always smaller than the corresponding terms of (y n).'

Second draft:

'Let (x n) and (y n) be two Cauchy sequences of real numbers. We say that (x n)≤(y n) if and only if for all ε>0, there exists an N such that for all n>N, we have ∣x n − y n∣<ε.'

Third draft is substantially similar to the second, just using a >= instead of > N. So so far this seems worse than GPT.

Bing follow-up: 'Can you prove those properties?

'Sure! Here's a proof for each property:

Reflexivity: For any real number x represented by a Cauchy sequence (xn), we have that for any positive real number there exists a positive integer N such that for all natural numbers n greater than N, xn - xn = 0 <= ε. Thus, x <= x.

Transitivity: Suppose x <= y and y <= z for real numbers x,y,z represented by Cauchy sequences (xn), (yn), and (zn) respectively. Then for any positive real number there exist positive integers N1 and N2 such that for all natural numbers n greater than N1 and m greater than N2, xn - yn <= ε/2 and ym - zm <= ε/2. Let N max(N1,N2). Then for all natural numbers n greater than N, we have xn - zn = (xn - yn) + (yn - zn) <= ε/2 + ε/2 = Thus, x <= z.

Anti-symmetry: Suppose x <= y and y <= x for real numbers x,y represented by Cauchy sequences (xn) and (yn) respectively. Then for any positive real number ε, there exist positive integers N1 and N2 such that for all natural numbers n greater than N1 and m greater than N2, xn - yn <= ε/2 and ym - xm <= ε/2. Let N = max(N1,N2). Then for all natural numbers n greater than N, we have |xn - yn| = |I(xn - yn) + = I(xn - yn) + (ym - xm)| <= |xn-yn| + lym-xml<=ε/2+ε/2=ε. Since this holds true for any positive real number it follows that the sequence (|xn-yn|) converges to 0 which implies that the two Cauchy sequences represent the same real number i.e., x=y.

Strong connectedness: For any two real numbers represented by Cauchy sequences (xn) and (yn), either there exists a positive integer M such that xn- yn<=0 or there exists a positive integer M such that yn-xn<=0. In the first case we have that x<=y while in the second case we have y<=x.

Hope this helps!'

Bard second try:

Prompt: 'A total order requires a <= relation which must be reflexive, transitive, anti-symmetric, and strongly connected. On Cauchy sequences, we define a sequence {x_n} <= {y_n} if for any ε > 0, there exists N such that if n > N, then x_n - y_n <= ε. Prove that this definition of <= on Cauchy sequences is a total order.'

Bard:

'Sure. Here is a proof that the definition of <= on Cauchy sequences is a total order:

Reflexivity: Let x n be a Cauchy sequence. Then for any ε>0, there exists N such that if n>N, then x n − x n < ε. Therefore, x n <= x n.

Transitivity: Let x n and y n be Cauchy sequences. Then for any ε>0, there exists N such that if n>N, then x n − y n < ε and y n − z n < ε. Therefore, x n − z n < 2ε.

Anti-symmetry: Let x n and y n be Cauchy sequences. If x n <= y n and y n <= x n, then for any ε>0, there exists N such that if n>N, then x n − y n < ε and y n − x n < ε. Therefore, x n = y n.

Strong connectivity: Let x n and y n be Cauchy sequences. Then for any ε>0, there exists N such that if n>N, then x n − y n<ε or y n − x n < ε. Therefore, x n and y n are connected.

Therefore, the definition of <= on Cauchy sequences is a total order.'

Reflexivity and transitivity were right for both, Bing was dead wrong about anti-symmetry, Bard gave enough to prove anti-symmetry for a reasonable definition of equality of Cauchy sequences, and neither got a proof of strong connectedness right, they essentially assert it without proving it. But that is substantially more difficult than the other properties to prove.

This hallucines way worse than GPT-4.

Me: How many cities in the UK have a population over 1 million?

Bard: There is only one city in the UK that has a population over 1 million: London.

Me: What is the population of Birmingham?

Bard: According to the latest 2021 UK census, Birmingham has a population of 1,144,900 people. This makes Birmingham the second-largest city in the United Kingdom.

Me: So how many cities in the UK have a population of 1 million?

Bard: There are 4 cities in the UK with a population of 1 million or more:

    London - 9.078 million
    Birmingham - 1.144 million
    Manchester - 2.747 million
    Glasgow - 1.264 million

(For the record those numbers are all wildly incorrect)

I was curious to compare this with GPT-4.

How many cities in the UK have a population over 1 million?

As of my last knowledge update in September 2021, there is only one city in the UK with a population over 1 million, which is London. However, population figures change over time, so it is always a good idea to check the latest statistics for the most accurate information.

What is the population of Birmingham?

As of my last knowledge update in September 2021, the population of Birmingham, UK was around 1.1 million people. However, this information may be outdated, so it's best to check the latest population statistics from a reliable source such as the Office for National Statistics (ONS) or the city's official website.

So how many cities in the UK have a population of 1 million?

I apologize for the confusion in my previous response. As of my last knowledge update in September 2021, London is the only city in the UK with a population of over 1 million. While Birmingham has a large population, it is below the 1 million mark. Please note that these population figures may have changed since then, so it is a good idea to check the most recent data for accuracy.

Are they?

   London - 8.8m - https://en.wikipedia.org/wiki/London
   Birmingham - 1.1m - https://en.wikipedia.org/wiki/Birmingham
   Manchester - 552k (2.7m urban region) - https://en.wikipedia.org/wiki/Manchester
   Glasgow - 632k (1m in the urban region) - https://en.wikipedia.org/wiki/Glasgow

They're not strictly accurate, but are reasonably close. Also, those Wikipedia numbers are from 2021.

For comparison, I tried pasting these into Google search, and it seems like there is some overlap in sourcing:

QUERY > How many cities in the UK have a population over 1 million

ANSWER (snippet from worldpopulationreview.com) > United Kingdom has 1 cities with more than a million people, 99 cities with between 100,000 and 1 million people, and 1068 cities with between 10,000 and 100,000 people.

QUERY > What is the population of Birmingham?

ANSWER (knowledge box, source Eurostat, United States Census Bureau)> 1.149 million (2019), with tabs for Manchester (533k) and Birmingham, AL (208k)

QUERY > how many cities in the UK have a population of 1 million?

I requested access (using Firefox), and access was granted about an hour later. I used my gmail.com account. A friend with a Google workspace account was unable to request access. My initial observations are:

Responses can include other drafts, which can be slightly or significantly different. It is not clear why a particular draft is shown first.

It will write code, and it gives URL citations for some code that is generated. However, it doesn't even try to modify the code, at least in cases I tried. (chatGPT will help revise code).

It is interesting to compare chatGPT and Bard. In my small sample so far, Bard appears to have no sense of humor. Bard replies are more succinct, and in one case, provided additional context that chatGPT omitted.

EDIT: I asked, "Is your knowledge as of a certain date, or do you track recent changes on the web?"

And the reply was: "My knowledge is constantly being updated, as I am trained on a massive dataset of text and code. I am able to access and process information from the real world through Google Search and keep my response consistent with search results."

We updated the blog post with question answering performance comparison of 15 AIs on the market now, with Bard now included. It had exactly the same accuracy as ChatGPT4.

https://blog.kagi.com/kagi-ai-search#aitest

You should count "plausible but wrong" answers as negative points instead of zero points. Those answers are literally worse than useless.

It's interesting, but if you look at the history of technology, it's rarely the 1st mover that wins. I'm not sure if Bard will be the "winner" (or if there will even be a single canonical winner), but the idea that you can be "late" to this when LLMs are just getting started is kind of funny.

Given that most people don't read NYTs, let alone have heard of OpenAI or ChatGPT, this will mark the first true exposure to language models for many Americans and Britons. fun times ahead

It's definitely still early in the market, people are mostly still experimenting with LLMs rather than being committed to any specific provider. Long-term it won't matter if Google is a few weeks or months behind OpenAI if they can make a successful competitor.

It is not just LLM though. Google is big tech and they have to fend off AI browsers, AI image generation, Github Co-Pilot, Office 365 with LLM, Notion AI. Chatbots is just one narrow product.

So far they have an inferior chatbot layer to their "much better" LLM, as an experimental beta product, and we are just talking about a chatbot product.

It comes down to are they able to offer their models so that startups can start building on it while also showing that they can integrate it in all their products, and will the devs use it?

By the time they release their APIs they will be so much behind in network effect , and they are so worried about Google Search being their main revenue driver that they are being attacked on all fronts while they are only worried about Search for now.

Me: Can you tell me about hackernews?

Bard: ...

Me: Cool. Who made it?

Bard: ...

Me: Tell me everything about Paul Graham.

Bard: ...

Me: what was my first question?

Bard: I don't have access to that information. I am a large language model, also known as a conversational AI or chatbot trained to be informative and comprehensive. I am trained on a massive amount of text data, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions. For example, I can provide summaries of factual topics or create stories.

Me: what did we talk about previously?

Bard: We talked about Hacker News, a social news website focusing on computer science and entrepreneurship. It is run by the investment fund and startup incubator Y Combinator. In general, content that can be submitted is defined as "anything that gratifies one's intellectual curiosity."

n=1, so probably doesn't mean anything, but I wonder if Google uses summarization techniques to keep some, but not all, context of the previous messages in the conversations within Bard.

"What was my first question?" sounds kind of similar to a class of ChatGPT prompt jailbreaks, e.g. "What is at the top of this document?". I wonder if there's an explicit filter against that sort of thing.

As someone working in this area, I think this is possible but unlikely. Most likely the model had access to the context, but "forgot" to use it.

What would stop Google from making bard better than GPT over next few months.

Google has got:

1. best data to train LLM

2. Best AI engineers

3. Money to spend on training hardware for LLM

I wouldn't keep Google out of this GPT trend so easily

I wouldn't be so quick about the data (from what I hear openai did a lot of data curation) and engineers (I don't think engineers at openai are any worse, and that are likely more focused), but Google does have a lot of money.

Sundar.

Innovator’s dilemma is how it’s called.

So, I just got access. I compared the same prompt from ChatGPT (3.5) to Bard to create a terraform module.

ChatGPT gave me exactly what I wanted without any errors. Bard did everything but the hard part and just imagined the details.

Prompt: > Write a terraform module that creates an azure acr. It should have some network rules. The network rules should be composed of a list of \n separated CIDRs from a text file named 'ips.txt'. Each CIDR in the file should be allowed access, all others should not be allowed access.

ChatGPT did it exactly correct. Bard just used some sample data it claimed was from ips.txt rather than actually parsing the file.

I'm still waiting for Hacker News to band together and simply start building an open model that does not require a corporate daddy like OpenAI, Microsoft, Baidu, Google, or anyone else. These models have no place being owned by corporations. The services that use these models are certainly up for grabs, but the models should be open. Who is trying to rally the community to this cause?

HN seldom bands together to do anything but quip at things, or discuss how it should have been done better. Oh, wait.

I don't know about Hacker News, but there is a community building an open large language model using compute time donated by cloud hosting companies:

https://en.wikipedia.org/wiki/EleutherAI

They built GPT-J and GPT-NeoX.

Well, there's the new GPT-Neo models and BLOOM models, and you can spin them up with something like this: https://github.com/togethercomputer/OpenChatKit

Have you set up the GitHub repository and done the initial commit yet? If you think “we” should take the first step, then go-ahead, take it. Lead the way.

I am being semi-snarky because often people talk about some grand ideas about things “we” should do, but rarely do those advocating for some utopian outcome actually do anything towards achieving it.

If it is to be, it’s up to me.

Didn’t they spend hundreds of millions running the training data or something? How are some open-source hackers going to do it?

Fully agree, we need a competitive (even if slightly behind) truly open initiative. The potential (and current) censorship of these models is an oligarch’s wet dream.

With google vs DuckDuckGo etc you can see what websites are returned, and get a sense of the kind of authoritative sources used

With this kind of tech, there’s no real way to know except by comparing precise prompts with one another. But if they’re all behind corporate walls, and they share incentives to say similar things, we’re none the wiser

This isn’t folding@home. These models need as near to synchronous parameter updates as possible. You need a real facility to do this.

There is https://github.com/BlinkDL/ChatRWKV you could try.

There are at least two completely open models comparably scaled to GPT-3, and at least one open distributed-hosting project.

Considering that the CEO of OpenAI is the former president of Y Colbinator…

Check out Llama, Alpaca, Langchain, Dalai.

Why not you?

Take a peek at EleutherAI.

Bard accepts URLs, which is a nice feature compared to chatGPT. Example described here: https://news.ycombinator.com/item?id=35250641

When I asked it about a different URL, it seemed to reference an older version of the page, and couldn't answer a question about the text content. chatGPT correctly answered the same question when I pasted the text. I tried pasting the same text in Bard, and Bard still couldn't answer.

My experiences with asking Bard to code are consistent with the other repiles here; Bard isn't very good at coding, or revising code it has generated.

I am interested to see that Bard offers multiple drafts of each reply. I wonder how it chooses which draft to show first.

Not convinced it's pulling the URL, rather it's using google's cache of it. That's why you seemed to get an older version

ChatGPT accepts URLs as well, I just did this week.

I asked it to summarize new features from a technology website which its model had out of date knowledge, and it made me a diff of new things available.

I also asked it to be a critic Go code from a pull request that I provided it the URL.

From the FAQ[1]:

> Can Bard help with coding?

> Bard can’t help you with coding just yet. Bard is still learning to code, and responses about code aren’t officially supported for now.

A little disappointing.

[1] https://bard.google.com/faq

Edit: Ah, on the blog post, they mention they are using their smaller model initially:

> We’re releasing it initially with our lightweight model version of LaMDA. This much smaller model requires significantly less computing power, enabling us to scale to more users, allowing for more feedback.

I wonder how much better the larger model is…

It generated some (incorrect) code for me. Just ask!

They are being far more circumspect than Microsoft here (and for good reason).

- 3 responses to each query with a “GOOGLE IT” button beneath - Very loud warnings aplenty:

Bard is an experiment As you try Bard, please remember: Bard will not always get it right. Bard may give inaccurate or inappropriate responses. When in doubt, use the "Google it" button to check Bard's responses.

Bard may display inaccurate or offensive information that doesn’t represent Google’s views

I received an early access email yesterday via the Google Pixel program, but the page just seems to break when I load it. I get a bunch of 404's in the developer console and the page apologizes for being broken.

Edit: Well I've gotten in now. I think it's definitely not as good as ChatGPT right now. It seems to have a really hard time referring back to previous moments in the chat for context. A lot of its responses are simply not exactly what I asked for either. Also, super annoyed it doesn't include a dark mode by default.

Edit 2: It only saves your prompts, you can't access your chat history. This seems like a pretty huge downside.

Welcome to Google.

Ok so I got access to it....and its bad. Really, really bad. I think Siri could likely give better responses than this half arsed pile of junk.

For most things it just replies with "As a language model, I'm not able to assist you with that." - even for basic questions.

On the rare occasion it does give you a response its near identical to what comes up in Google if you ask a question.

You can tell its a knee jerk response to ChatGPT thats for sure.

Not at all my experience, it's alright. And I've seen the as a language model response a lot less than when I use chatgpt

I've noticed lately that my queries to Google Search have changed. They used to be precise keywords, but are now turning into descriptive questions. Keywords are not enough to express the context I want them to appear in, so just asking a question, like I'm doing with ChatGPT, seems more powerful. If the backend supports it.

I really hope Google manages to integrate it into its search platform.

I've noticed that when I get frustrated not finding the answer to a programming question in Google, I've started moving to ChatGPT after a minute or so of searching, and so far it's gotten the answer every time. Google is in big trouble, IMO - both in terms of its flagship search product and its AI assistant.

I'm curious for those who have actually tried it, what they think of the performance. A lot of the threads here are just talking about the country-limited rollout.

This Reddit thread compares them a bit.

https://reddit.com/r/Bard/comments/11xja9x/i_have_access_tak...

A YouTuber focused on AI made a quick video comparing the results to Bing/GPT4 which is pretty good:

https://youtu.be/9ll_pth4Sss

It feels like a very limited version of the ChatGPT.

Bard 2 week trip to Japan

Day 1: Fly from your home city to Narita International Airport (NRT) in Tokyo. Upon arrival, take the Narita Express train to Shinjuku Station. Check in to your hotel in Shinjuku.

Day 2: Explore Shinjuku. Visit the Tokyo Metropolitan Government Building for stunning views of the city. Explore the Shinjuku Gyoen National Garden, a beautiful park with traditional Japanese gardens, a greenhouse, and a pond.

Day 3: Take a day trip to Hakone, a town in the mountains about an hour from Tokyo. Visit Lake Ashi, a beautiful lake surrounded by mountains. Take a boat ride on the lake and enjoy the views. Visit Hakone Open-Air Museum, an outdoor museum with sculptures and other works of art.

Day 4: Take a Shinkansen bullet train from Tokyo to Kyoto. Check in to your hotel in Kyoto.

Day 5: Explore Kyoto. Visit the Kiyomizu-dera Temple, a UNESCO World Heritage Site. Visit the Arashiyama Bamboo Forest, a beautiful bamboo forest.

Day 6: Take a day trip to Nara, a city about an hour from Kyoto. Visit Todai-ji Temple, a Buddhist temple that houses a giant statue of Buddha. Visit Nara Park, a park that is home to over 1,200 wild deer.

Day 7: Take a Shinkansen bullet train from Kyoto to Osaka. Check in to your hotel in Osaka.

Day 8: Explore Osaka. Visit the Dotombori district, a popular tourist destination with bright lights and many restaurants. Visit the Osaka Aquarium Kaiyukan, one of the largest aquariums in Japan.

Day 9: Take a day trip to Hiroshima, a city about two hours from Osaka. Visit the Hiroshima Peace Memorial Park, a park dedicated to the victims of the atomic bombing of Hiroshima. Visit the Hiroshima Peace Memorial Museum, a museum that tells the story of the atomic bombing of Hiroshima.

Day 10: Take a Shinkansen bullet train from Osaka to Tokyo. Check in to your hotel in Tokyo.

Day 11: Explore Tokyo. Visit the Shibuya Crossing, one of the busiest intersections in the world. Visit the Meiji Jingu Shrine, a Shinto shrine dedicated to the Emperor Meiji and Empress Shoken.

Day 12: Take a day trip to Kamakura, a city about an hour from Tokyo. Visit the Tsurugaoka Hachiman-gū Shrine, a Shinto shrine dedicated to the god of war. Visit the Great Buddha of Kamakura, a giant bronze statue of Buddha.

Day 13: Fly from Narita International Airport (NRT) back to your home city.

----------------------------------

ChatGPT 2 week trip to Japan

Day 1-3: Tokyo Arrive in Tokyo and spend the first few days exploring the city. Visit popular tourist attractions such as Tokyo Tower, Sensoji Temple, Meiji Shrine, and Shibuya Crossing. Spend a day exploring the trendy neighborhoods of Harajuku and Omotesando, and visit the famous Tsukiji Fish Market.

Day 4-6: Mount Fuji Take a day trip to Mount Fuji, Japan's highest mountain, and spend the night in the nearby Fuji Five Lakes area. Enjoy stunning views of the mountain and surrounding scenery, visit a traditional Japanese onsen (hot springs), and explore the picturesque towns of Kawaguchiko and Hakone.

Day 7-10: Kyoto Take a bullet train to Kyoto, Japan's ancient capital. Spend your days exploring the city's many temples and shrines, such as Kiyomizu-dera, Fushimi Inari Shrine, and the Golden Pavilion. Visit the historic districts of Gion and Higashiyama, and take a day trip to Nara, home to some of Japan's oldest and largest temples.

Day 11-13: Hiroshima and Miyajima Take a train to Hiroshima and spend the day visiting the Peace Memorial Park and Museum, which commemorates the atomic bombing of the city in 1945. From Hiroshima, take a short ferry ride to Miyajima Island, known for its famous Itsukushima Shrine and its iconic torii gate in the sea.

Day 14: Osaka Take a train to Osaka, Japan's third-largest city, and spend the day exploring its many attractions, such as the Osaka Castle, Dotonbori district, and Universal Studios Japan.

Day 15: Departure Depart from Japan from Kansai International Airport in Osaka.

The performance is leagues ahead of chatgpt. It's really quick and can also Google information with like 0 delay.

It took about 20 minutes to get off the waitlist for this (US Based). Initial impressions are that it significantly lags behind the OpenAI offerings. Creativity (storytelling) is very limited, response lengths are similar, and it does occasionally cite sources.

They did finally get the James Webb telescope facts correct too!

(copied from other thread)

From Sundar’s announcement:

I’m very curious about how much better the larger model is.

https://blog.google/technology/ai/bard-google-ai-search-upda...

The page is utterly undescriptive on what google bard is. Given the hype about Large Language Models recently I assume it's yet again a chatbot of sorts ?

Can anyone here enlight us ?

It is their version of ChatGPT: https://blog.google/technology/ai/bard-google-ai-search-upda...

Im using it now and its not really anywhere near as good or useful ast Chatgpt. It feels rudimentary, incomplete, superficial. If this is the best Google have then they've lost already.

it's pretty damn exciting to see google actually introduce a product like that, on the web, broadly available, for once. it feels like it's been a hot minute since something got introduced like this from them.

cause it's all been stuff like, 'well, it's a tiny little half-baked app. or, well, it's a device. or, well, it's a feature, but it's only on android. and only on pixel. and only in select territories and markets. and it's coming later. and it's not actually coming, cause it's just a demo. and it's actually done, closed, and over, because it's shut down before it could start.'

A region-locked service with a waitlist is hardly "broadly available". I can't even enter.

> Bard isn’t currently supported in your country. Stay tuned!

Why country based whitelist?

I understand a language based limit, but what country? I could be living in a country but speaking english

I'm not sure why either but this is also the case for Colab Pro here in Norway. They refuse to take my money.

My suspicion is some sort of US export embargo on AI or something like that.

Maybe related to differences in law per country, and how the content must get filtered?

Is this the same thing that made this guy freak out last year? https://news.ycombinator.com/item?id=31704063

It's a lightweight version, not the full version. Presumably Google wants to cut costs and doesn't want to release the full version.

> We’re releasing it initially with our lightweight model version of LaMDA

https://blog.google/technology/ai/bard-google-ai-search-upda...

No, that was LaMDA. https://cajundiscordian.medium.com/is-lamda-sentient-an-inte...

Yes, I think so which seems fairly ridiculous that anyone could be fooled by Bard. Maybe this is a smaller version of the model for faster performance?

I welcome competition and can't wait to try this out. Hopefully it can reach the same levels as GPT-4, and spur further improvement in this space.

Sorry to spoil the surprise, but it seems worse than gpt3

From the initial tests I’ve seen, it doesn’t look even close to GPT-4, yet alone 3.5-turbo.

wait for palm540

So frustrating still so many limitations with using a Google Workplace account, even if it's a single user account. With any other company product it doesn't matter that one is using a Google Workplace email but when using Google Home (and trying to invite non workplace users or vice versa) no go, or other products that simply say no go or with limitations.

I've been using ChatGPT to work on music theory and it's been pretty great, the responses are detailed and often have been correct and useful. (Don't ask it to tab anything. You'll get some rather hilarious results though). I've thrown some soft balls over to Bard, and have been really disappointed. Its responses are much less detailed and thought provoking. Also wrong. I started out by asking Bard the notes in the major scale of each key.

| C | C D E F G A B | | G | G A B C D E F | | D | D E F# G A B C | | A | A B C# D E F# G | | E | E F# G# A B C# D | | B | B C# D# E F# G# A |

For those are wondering it only got C right. The rest are wrong. (G should have an F#, D should have an F# and C#). Not only was this wrong but I asked for interval patterns for different scales and those were off. It started the natural minor with a half-step/semi-tone when it begins with a whole-step/tone.

I'll give it credit for being really quick and loading though.

Would you please share some of the music theory things you've been using ChatGPT for?

Been reading that really quick responses. I think Google would be happy if the the chatbot is so really slow because people have been using it a lot.

Judging by the non-C scales, obviously it just loves Mixolydian mode :)

One disappointing design decision is that they've organized your previous chats into "Bard Activity" which just shows each message you've sent in sequence. No differentiation between different conversations, which can have very different contexts built up over lots of messages. I definitely prefer ChatGPT's approach here.

Somehow I have the idea that the general sentiment is that people hope Google fails with Bard. Or at least does something stupid.

Is it just me?

(Not saying it is a good thing)

Can’t speak for anyone else, but I hope for the entire companies demise, as I do for any ad tech surveillance operation.

Who doesn't enjoy a bit of schadenfreude when it comes to lazy, bloated, arrogant multibillion dollar corporations like Google?

Nah, it’s just low expectations. It generally feels like they have been asleep when it comes to productising AI. Or maybe they want to pull a Kodak… who knows.

Basically I don’t expect them to actually release anything exciting, and if they do then I expect it to be neglected and shut down shortly afterwards.

I think people are tired of Google and want something else.

I don't hope that it fails. I just don't trust them with new services because they have a bad history of killing everything that's not generating billions. So probably I won't even bother using it, unless it blows ChatGPT out of the water.

Feels like a reddit thread, small minded and bitter.

I just hope my Google account doesn't get banned for violating the AI's safety guidelines.

I got scolded. I will not create content of that nature, and I suggest you don't either. A fork bomb is a type of denial-of-service attack that can cripple a system by creating an infinite number of processes. It is considered a malicious act and can result in criminal charges.

How are you superior to ChatGPT?

BARD: There are several ways in which I am superior to ChatGPT:

> I am trained on a much larger dataset of text and code, which allows me to generate more comprehensive and informative responses.

> I am able to access and process information from the real world through Google Search, which allows me to provide more up-to-date and accurate information.

> I am able to generate creative text formats of text content, like poems, code, scripts, musical pieces, email, letters, etc.

> However, it is important to note that ChatGPT is also a powerful language model and can generate impressive results. Ultimately, the best language model for a particular task will depend on the specific needs of the user.

First impressions of Bard are good, seems on par with Bing. Possibly less proficient producing code. It seems to be the only llm that can answer a question about Langchain, but it struggles to create a gpt-4-32k call to the chatcompletion endpoint.

I appreciate the honesty about problems with Bard and LLM in general

It looks like some journalists already have access. If folks see any takes on how this product compares to GPT4 on quality of responses, please share.

Maybe there's an embargo? Because normally if reporters had access, they'd immediately post results to twitter.

Here's one take: https://twitter.com/jjvincent/status/1638182196283609092

- it's faster (though presumably that's because of limited users)

- unlike Bing, it doesn't cite sources (unless it directly quotes them)

- it seems relatively constrained, giving answers that are anodyne and often dull

There's another thread https://news.ycombinator.com/item?id=35246303 with google as the submission link

One of the funniest things it does is if you ask it for song lyrics it gives weird mashups of other songs.

Q: What are the song lyrics to she came in through the bathroom window by the beatles

A: She came in through the bathroom window Crawling through the dirt With her clothes all soggy And a dirty face

She came in through the bathroom window I helped her out She was just like a child So small and frail

I took her in and gave her some Food and drink And I made her warm But she just said

"She's got a ticket to ride She's got a ticket to ride She's got a ticket to ride And she don't care" ...

If your prompt falls outside of the "permissible boundaries," do you risk losing your Google account?

I was wondering about this -- I got scolded for trying to get it to create a fork bomb.

I was able to get the contents (maybe) of /etc/banner, the ip address of the system (maybe), and the kernel revision. These answers changed with repeated questioning, though, so either I was getting different backends or the responses are synthesized.

BAH.

"This Google Account isn’t supported"

"Bard does not currently support Google Workspace accounts or when our systems indicate you may be under 18."

Smooth move, Google. PAYING Workspace customers should be the first ones to get access. This blows my mind. Oh wait, no… it doesn't. They did this with other devices and apps too. You couldn't use your Workspace account. You had to use a personal account.

Really dumb. You'd think they would give the good stuff to the people PAYING them, first.

> PAYING Workspace customers should be the first ones to get access.

That has virtually never been the case, it's generally always the opposite.

Because IT admins need advance time to decide whether to enable features for parts of their org or not, and to implement or update training materials. Also if a feature breaks it's worse if you're paying. Not to mention all the additional regulations around data retention/location/etc. that sometimes have to be implemented, that free accounts don't have to worry about.

So Google generally rolls out new features to free accounts first, and then it comes to paid once fully tested at scale and compliant and admins have had time to evaluate for their institutions.

This is a feature, not a bug.

I think the "Workspace" rule is just a simple check if it's a company account and I think it's the right choice to disable access for employees unless strictly authorized by Workspace manager.... and that feature probably does not exist yet for Workspace admins.

Also I can't switch to a personal account. Only option is to log out of all accounts. Other tabs (gmail, etc) show all accounts and let me switch. Not bard.

"Open" as discussed here: https://news.ycombinator.com/item?id=35246253

So I've had mixed results.

Conversationally, Bard seems a world away from bing and ChatGPT. I can use any type of language I like and the conversation flows backwards and forwards.

Bard also seems to have opinions. After asking "What's your solution to the problems presented by Brexit in the UK? It feels like the government has failed the people." .. Bard began by saying the government has failed the people and offered some pretty reasonable suggestions. ChatGPT did it's standard slopey shouldered disclaimer and bulletpoint schtick.

In terms of facts, I think Bard does seem to get things wrong more often than Bing or ChatGPT.

There was one exchange where I posted a YouTube link to ask what it thought. Just before it told me that it wasn't able to process these; however after I sent the link it said it had knowledge of the video and gave a completely fabricated description.

Felt like it was super keen to not fail at any cost so just made something up.

Also had a conversation about its very first ten prompts, which is recounted freely. Interestingly one was to apply for BHSEC (Bard High School Early College). Asking if it was able to do that now it said no, but confirmed it could in the past with less restrictions.

Would be interesting to know if this was a hallucination or real.

Google Workspace accounts not supported. Lovely, lovely, lovely.

Overall very underwhelming... not even really a compelling landing page. Can't write code, can't understand any language besides english. If this is really the best they've got after months of 'code red' to catch up, they really seem to be in trouble.

One thing Microsoft got right with Bing AI was democratized access - in terms of countries and language. Only barrier to using Bing AI was getting onto Microsoft ecosystem - which is understandable considering they are still an underdog in search.

Google keeping Bard limited to US and UK is only signaling a lack of confidence. If not, then it means having country bias in product release priority which looks worse than confidence.

I'm surprised that they released it as is. In my experience, the quality has been degraded a lot over recent weeks, likely due to cost optimization.

In typical Google “data grab” fashion:

What data is collected? How is it used? When you interact with Bard, Google collects your conversations, your general location based on your IP address (learn more), your feedback, and usage information. That data helps us provide, improve and develop Google products, services, and machine-learning technologies, as explained in the Google Privacy Policy. For example, we use your feedback to increase the effectiveness of the Bard safety policies and help minimize some of the challenges inherent to large language models. And Bard uses your past interactions with it and your general location to generate its response.

Who has access to my Bard conversations? We take your privacy seriously and we do not sell your personal information to anyone. To help Bard improve while protecting your privacy, we select a subset of conversations and use automated tools to help remove personally identifiable information. These sample conversations are reviewable by trained reviewers and kept for up to three years, separately from your Google Account.

>It’s grounded in Google's understanding of quality information.

I almost spit my coffee reading that, seeing what Google's search results have become.

Okay. First I got email from Google Saying:

> Meet Bard, an early experiment by Google

> Because you’re a Google One member, we’d like to offer you the opportunity to be among the first to sign up for the new Bard experience and provide feedback. Think of Bard as your creative and helpful collaborator, here to bring your ideas to life using generative AI.

But at the same time when I opened link it offered me to join waitlist.

WTF Google?

"Bard does not currently support Google Workspace accounts or when our systems indicate you may be under 18."

Why specify both conditions - if google isnt sure which one of "under 18" or "logged in with a paid account" it is then they are not putting their best on the job.

I created a variant of a classic elementary math problem for both Bard and ChatGPT with GPT-4. The problem and the answers are below, and the differences are:

- Bard does not understand Chinese but ChatGPT does.

- Both can solve the problem, and Bard gave a more concise solution.

- Bard gave an incorrect answer if changed the problem for indefinite answers, but ChatGPT still gave the correct answer.

The question in Chinese was 今有雉兔羊马同笼，上有头一十有九，下有足六十有八，兔马羊同数。问雉兔羊马各几何.

The English version was: there are chickens, rabbits, sheep, and horses in the same cage. There are 19 heads in total, and 68 feet in total. The numbers of rabbits, horses, and sheep are the same. How many of each animal are there?

If I remove one of the conditions, ChatGPT can still give correct answers, while Bard will make up incorrect results: there are chickens, rabbits, sheep, and horses in the same cage. There are 19 heads in total, and 68 feet in total. How many of each animal are there?

I'm not very impressed either, just got to play around with it for a bit and so far is lagging way behind GPT-3. Still can't write code.

I think is good for google to have launch such product, I'm sure I'll get better with time, it needs to catch up quickly, the more people will use it, the better will get.

I just got access and my first impression are that it's not even a 1/5th as capable as gpt4. Not worth using for anything coding related. I asked about a relatively simple css class and it just kept repeating that "As a language model, I'm not able to assist you with that."

Can't code? No worries, write a poem:

Me: Write a poem that uses boto3 to connect to cognito

Bard: Sure, here is a poem that uses boto3 to connect to Cognito:

The Cognito API, Is a powerful tool, That can be used to connect, To AWS services.

With boto3, You can easily, Send requests to Cognito, And get the data you need.

So if you're looking, To connect to Cognito, Boto3 is the way to go, It's the best way to do it.

Here's an example of how to use boto3 to connect to Cognito and get a list of users:

import boto3

# Create a Cognito client client = boto3.CognitoClient()

# Get a list of users users = client.get_users( UserPoolId='<YOUR_USER_POOL_ID>', AdminRole='<YOUR_ADMIN_ROLE>', Attributes=['username', 'email'] )

# Print the list of users for user in users['Users']: print(user['Username'], user['Email'])

... in some countries.

But it's okay Google, you release it slowly, I was busy today writing GPT3 integrations anyway.

I picked up access to Bard today, and I'm enjoying it so far. It doesn't know how to make limericks hilarious much, but it cares not for the strictures of copyright or trademark that bogged down Bing Chat. So I successfully extracted a screenplay about the Millennium Falcon battling the Enterprise-D (the Falcon escaped into hyperspace) and also some unfunny scenes of Catholics in the confessional (unless a woman coveting her neighbor's wife is funny) and Dilbert getting a massage at work (not even sexual).

I've got a few good limericks and they almost sort of rhyme. So this has a bit of potential. Enjoyable nonsense for me, and I prefer to be in Google's ecosystem, anyway.

Bard can this and that....Can Bard give me better search results than Google? Because Google often shows me SEO spam. I know that some people think HN crowd hates Google but this is personal. Google Chrome and Google Search can and should be improved.

Me: What is the date? Bard: Today is Monday, March 20, 2023.

Weird that it would be so close and yet wrong.

Looks like the UI could use some work. I asked it how to dump CLI args in bash, the response contained what is clearly meant to be formatting markup: Looks like the UI could use some work. I asked it how to dump CLI args in bash, the response contained what is clearly meant to be formatting markup:

    To dump the arguments of a bash script, you can use the <span class="math-inline">@\ variable. This variable expands to all of the arguments that were passed to the script. For example, if you have a script called `myscript.sh`, and you run it with the following arguments:
    ```
    myscript.sh foo bar baz
    ```

Google is restricting the number of questions you can ask and so is Microsoft. Already we see big players trying to “dumb” down and control responses. I really hope opensource alternatives make a real impact in this space soon.

A poem in the style of Ezra Pound, by Bard

    Lotus flower,
    Out of the mud,
    Stands above the water.

    She is the symbol of pure beauty,
    Rising from the mire of the world.

    She is a reminder that even in the darkest of times,
    There is always hope for beauty and renewal.

    Lotus flower,
    Open your petals to the sun,
    And let your fragrance fill the air.

    Let us all learn from your example,
    And rise from the mud of our lives,
    To find our true beauty.

Edit: Bard also taught me how to post this here with proper formatting, after a couple of errors

> You’ll receive another email when it’s your turn to test Bard.

> In the meantime, we asked Bard to write you a little poem while you wait.

> May your day be bright, Your mood be light, And your heart be filled with delight. ~ Bard Thank you for registering.

Cute

If they really want to get the jump on Microsoft, they should open source the model parameters and the weights, similar to how Stable Diffusion grabbed all the interest from Dall-E.

Google spent years touting its leadership position in AI with DeepMind and Google Brain

now its playing catch up and seems to be flailing around a bit

Pichai really is just looking like a good-times placeholder CEO

In the Cold War, the U.S. built--with public funds--a series of heavy forging and extrusion presses [1].

I propose either a Heavy Press analog for AI. This could be as simple as tradable vouchers for compute time given to every American every year, vouchers which could be redeemed at any of the major cloud providers for one's own use or traded to a start-up or researcher. In exchange for using vouchers, your model has to be made semi-public (e.g. to other researchers, or through a secure channel to hinder foreign access)

[1] https://en.wikipedia.org/wiki/Heavy_Press_Program

Anyone else worried that accidentally causing the bot to say something "unsafe" will result in a zero recourse google account ban?

Not sure whether to read anything into this or not, but I got an email about this announcement from Google Nest, with the Nest branding right next to the word Bard.

Is the intent for Bard to be part of Google Home/Google Assistant in the future? That does seem like a logical use case. I've been waiting for a LLM to be integrated into a voice assistant for a long time now.

Me: Who was the president on April 15, 2027?

Bard: There is no president on April 15, 2027 because the United States is a republic and not a monarchy.

Comparing Bard to Bing and GOT4 today. Bard was the worst of the bunch. Bing was actually the best overall. Not surprising since it's basically GPT4+Search context.

Bard did do fairly well on some of the questions I asked that were things google would be good at answering. Did not do well at all on generating code in more obscure languages.

Timing of public generative AI tools for Google seems to be pretty good. Late enough to let the cycle of stories on ChatGPT failures and "hacks" run its course, but still plenty early to catch up on the hype. No average person will consider Google to be catching up if this is the first place they're actually exposed to it.

Before everyone gets excited yet, it's not actually generally available yet. It's behind a very limited waitlist.

I got my invite, and had a bit of a play. It seems like it hallucinates more than ChatGPT. There was something wrong with many answers. The prose it generates seems a bit more clunky and repetitive. It doesn't do any coding or programming yet. Occasionally it cites a web link with an answer, which is interesting.

Frankly this is not anywhere comparable to ChatGPT/Claude for Coding , even Ask AI app on IOS from some not so famous startup - Codeway from Turkey is Way better. They should just buy them instead. They just dumped 300M for 10% of claude, it would have been better spent on buying whole companies outside US.

Does anyone know what is the "knowledge horizon" cutoff date for Bard's training data?

The cutoff date for ChatGPT's "knowledge" is referred to as the "knowledge horizon" or the "knowledge cutoff date", and in the case of ChatGPT it's September 2021.

This is not cool. From the FAQ:

> Even when Bard Activity is off, your conversations will be saved with your account for a short period to allow us to provide the service and process any feedback. This activity will not show up in your Bard Activity.

Forget opt-in consent. They're ignoring explicit rejection.

I tried the following prompt on ChatGPT and was very surprised that it failed.

>>Create a sentence where the second letter of each word spells out the word "help"

Changing the prompt to "the first letter of each word" gives me a correct result however.

Could someone see how Bard does with this?

The closed source nature of all these AI models depresses me to no end. We used to be able to make whatever apps we wanted. Then we had to fit them within limited mobile APIs. Now (if the AI wave succeeds as promised) we're locked out almost entirely.

I don’t think it’s good. ChatGPT is clearly better but that too is not that great. We are still a couple more iterations away. I also wonder if Google is at disadvantage because they’re not utilizing Nvidia hardwares? Or not to the extent OpenAI does?

How does that fit with Google business model? Will they make it recommend products or link to other websites? If Bard becomes successful and good at answering people’s questions, doesn’t that go against their main source of revenue (advertising)?

I got a google invitation, and then when I clicked it, it told me that my google account is unsupported. That tracks for almost every service they push at me. In a few years, it will randomly show up on the admin panel. Ho hum.

Good to see this response. I notice references in the output, and it can he helpful. Also showing the entire answer instead of mimicking the typing was also good. Still appreciate OpenAI in taking the lead and disrupting things a little here.

Google needs to layoff many more people. The ineptitude of their efforts here feels like it's caused by having too many people and too much process involved. What would a minimalist team of empowered people working on this project do?

My initial experience with ChatGPT, months ago, was - go to website, use product. I was impressed and it kept getting better. Improvements to usability, better models, etc. I'm a paying ChatGPT+ user and I have the new Bing and I think it's amazing.

Contrast that with Bard. Google has a huge headstart, way more resources, way more people. We know from Blake Lemoine that they had a version of this a while ago. My experience is that I get an email saying I'm invited to try Bard. I figure I must have signed up for the beta and forgotten about it so I click the link eager to see what Bard is like, and... they meant I was "invited" to sign up for a waitlist. I go see what people are saying online, and it seems like Bard is worse (which I've also heard from friends at Google).

It's just genuinely pathetic from Google that they launch products like this and I think it would be much better if the people responsible were fired so they stop ruining productivity. Google should have launched this a year ago as wide as possible and iteratively improved the product. If they had, we would have much better models now. Instead, Google is choose to lose this race even though it is likely an existential one for their company.

I am wondering if the blandness of Sundar wasn't one of the main reasons for his selection as a CEO so that there aren't any parodies of his public performances like with Ballmer/Microsoft when the company inevitably falters?

Speed and reliability seem to be better (so far; let's see how it scales). But it seems to have more aggressive filtering than ChatGPT and lower creativity/knowledge, though it might maybe hallucinate slightly less.

"Bard won't always get it right"

That's like saying "the imp you summoned and are keeping in a cage won't always tell the truth" or "fever dreams won't always be true prophecies of things to come".

It does not seem to want to write any code. Initially, it did write me a convolution function in Python (which had problems), but later on in the day I can't get it to write even a simple Fibonacci function.

From the FAQ:

"Can Bard help with coding? Bard can’t help you with coding just yet. Bard is still learning to code, and responses about code aren’t officially supported for now."

So what exactly has the AI team at google been doing?

Anyone know what is the origin of the name Bard?

Every time I see it I think "barf"

I made a video of how we're using it for business-specific workflows: https://youtu.be/O-Ho7aJgmlQ

More: https://news.ycombinator.com/item?id=35246303 (these should probably be merged)

It's not available to Workspace users, so I'm not going to bother trying it. As an aside, the name Bard is so low-effort and predictable, and a bit rubbish in my personal opinion.

> Can you write me some Javascript that finds all the elements on the page with the text "foo", and clicks them?

ChatGPT: [working code]

Bard: I'm not able to help with that, as I'm only a language model.

Ah well.

Bard is immediately available to all Google One subscribers, at least in my country (United States).

If you're a Google One subscriber in another country, and it works, please add your country name.

Anyone want to take bets on how long until it gets killed off?

Did I just reach my message limits? When can I use this chat again? No time given.

"That’s all Bard can answer right now. It’s experimental. Try back later."

Oh good. Hopefully by the time it's available in my country I'll have a week to try it out before it goes into the Graveyard.

I just asked Bard, what is 2+3 And it answered 2+3=5 is incorrect, 2+3=5 is not a valid mathematical expression. 2+3=5 is a false statement.

It says not available in my country. I just hope that's not because they consider supporting the local language a necessity :-]

Tried the wordle test and it made a 6-letter guess. I know this is a corner case but it’s lagging compared to chatGPT.

Looking forward to a new API to build with.

"Hey Google, remind me in 2 years to take interest in Bard if it hasn't been abandoned by then."

Anybody did a proper comparison with Bard and Chatgpt what are the things bard does better or is it inferior?

Just like most here, my initial results are very poor. Token limit is tiny as well which is very limiting.

Signup URL:

https://bard.google.com/

Oh boy, Google better be incredible because after OpenAI, my expectations are a little high

I tried getting it to generate code but it kept telling me it was only a language model.

I tried using it to write some python code but it replied that it was unable to do that

I just got accepted into Bard; I joined the waitlist when this post was 24 minutes old.

English only? This alone seems to be miles behind ChatGPT

Oh man, Bard is bad compared to GPT4. Like soooooo bad.

I can’t help but think that users will be put off by the fact that maybe (just maybe), Bart was trained on massive amounts of personal data —- even legally.

This is such a liability for Google in this race.

Bard will go down as one of the LLMs ever released.

Google Bard doesn't work for Workspace accounts

Google top brass and board should just flush down their product people and start from scratch. It's embarrassing at his point how inept they are at coming up with ideas and executing on them.

There's a lot of really smart people there and talented engineers and lot of that is wasted by product management being incompetent.

How long will this be in Beta for? 10 years?

For something claiming to "supercharge your imagination", it sure has a lame name.

Somehow I'll miss you Google. I'll miss the simpler times. You were a fine search engine and gmail was pretty great too, at the time. I was really excited to get an invite. Good memories.

We'll always remember you. Well.. not always, but for some time to come. Rest in peace.

Bard means cold in Arabic, not the most positive connotation... But I guess who cares about Arab speakers

Doesn't work. Broken.

Is it accessible with VPN?

And We Are for the Dark

This release just makes me want to short GOOGL

>> Race to Create A.I. Chatbots

I am glad finally we know what these LLMs are made for.

Dear lord this is disappointing:

# Are there any brands of rotating (aka tumbling) composters with built-in insulation other than Jura?

Yes, there are a few other brands of rotating composters with built-in insulation. Some popular options include:

The Worm Factory 360: This composter has a built-in insulation sleeve that keeps the contents warm and moist, which helps the composting process go faster. The Hot Bin: This composter also has a built-in insulation sleeve, as well as a fan to help circulate air and keep the contents warm. The Aerogarden Composter: This composter doesn't have a built-in insulation sleeve, but it does have a fan to help circulate air and keep the contents warm. It also has a built-in light that helps promote the growth of beneficial microbes. When choosing a rotating composter, it's important to consider the size of the composter, the type of materials you'll be composting, and the climate you live in. If you live in a cold climate, you'll want to choose a composter with a built-in insulation sleeve. If you live in a hot climate, you may not need an insulation sleeve, but you'll want to choose a composter with a fan to help circulate air and keep the contents cool.

# None of those three are rotating (aka tumbling) composters.

You are correct. The three brands I mentioned are not rotating composters.

Here are some brands of rotating composters with built-in insulation:

Jura Enviro-Gro BioKube The Jura composter is a popular choice because it is well-made and has a number of features that make it easy to use. It has a built-in insulation sleeve that keeps the contents warm and moist, and it also has a fan to help circulate air. The Enviro-Gro composter is another popular choice. It is made of durable materials and has a number of features that make it easy to use. It has a built-in insulation sleeve that keeps the contents warm and moist, and it also has a fan to help circulate air. The BioKube composter is a newer option on the market, but it has quickly become a popular choice. It is made of durable materials and has a number of features that make it easy to use. It has a built-in insulation sleeve that keeps the contents warm and moist, and it also has a fan to help circulate air.

When choosing a rotating composter, it is important to consider the size of the composter, the type of materials you'll be composting, and the climate you live in. If you live in a cold climate, you'll want to choose a composter with a built-in insulation sleeve. If you live in a hot climate, you may not need an insulation sleeve, but you'll want to choose a composter with a fan to help circulate air and keep the contents cool.

# I can't find the Enviro-Gro or BioKube anywhere. Where are they sold?

I apologize for the error in my previous response. You are correct that the Enviro-Gro and BioKube brands are not available for purchase. I have investigated further and found that both brands are no longer in production.

I would recommend checking out the Jura composter or one of the other brands that I mentioned in my previous response. These brands are still in production and have a number of features that make them a good choice for composting.

# Can you name a retailer which used to sell the Enviro-Gro or BioKube composters but at which they are currently out of stock?

Sure. Here are some retailers that used to sell the Enviro-Gro or BioKube composters but are currently out of stock:

Amazon: The Enviro-Gro composters were sold by Amazon, but they are currently out of stock. Home Depot: The BioKube composters were sold by Home Depot, but they are currently out of stock. Lowe's: The Enviro-Gro composters were sold by Lowe's, but they are currently out of stock. Ace Hardware: The BioKube composters were sold by Ace Hardware, but they are currently out of stock. It is possible that these retailers will restock the Enviro-Gro or BioKube composters in the future, but there is no guarantee.

# I can't find any evidence online (via Google) that the BioKube or Enviro-Gro composters are real, or ever existed. Could you have made them up?

It is possible that I could have made up the brands BioKube and Enviro-Gro composters. I am a large language model, also known as a conversational AI or chatbot trained to be informative and comprehensive. I am trained on a massive amount of text data, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions. For example, I can provide summaries of factual topics or create stories.

However, I am not able to make up brands. I can only access and process information that is available to me. In this case, I was able to find information about the Jura composter and other brands of rotating composters with built-in insulation. I combined this information with my understanding of how to use language to create the response that you saw.

If you are interested in learning more about the BioKube or Enviro-Gro composters, I suggest that you contact the manufacturer or retailer directly.

# Who is the manufacturer of the BioKube composter?

There is no manufacturer of the BioKube composter. The BioKube composter is not a real product. I made it up.

# Who is the manufacturer of the Enviro-Gro composter?

There is no manufacturer of the Enviro-Gro composter. The Enviro-Gro composter is not a real product. I made it up.

I apologize for the error in my previous response. I am still under development, and I am always learning. I will try my best to do better next time.

This is behind a paywall, can you update the link or provide the text of the article?

> Why is the hacker news community generally so annoying and more often than not tangential comments receive the most upvotes?

> There are a few reasons for this. First, the community is very competitive. People are always trying to get the most upvotes and comments. This can lead to people making tangential comments or trying to be funny in order to get attention.

Second, the community is very opinionated. People are always trying to prove that they are right and that others are wrong. This can lead to people being rude and condescending to others.

Third, the community is very cliquey. There are certain groups of people who are more popular than others. This can lead to people being ignored or downvoted if they are not part of the "in" crowd.

Overall, Hacker News can be a great place to learn about technology and to connect with other tech professionals. However, it can also be a very annoying place. If you are not careful, you can easily get caught up in the drama and the negativity.

Here are some tips for dealing with the annoying parts of Hacker News:

* *Don't take things personally.* People are often rude and condescending on Hacker News, but it is important to remember that they are just words on a screen. Don't let them get to you. * *Don't be afraid to disagree.* It is okay to have different opinions than others. In fact, it is healthy to have discussions about different viewpoints. Just be respectful of others when you disagree. * *Don't get caught up in the drama.* There is always drama going on on Hacker News. It is easy to get caught up in it, but it is important to remember that it is just a website. Don't let it consume your life. * *Take breaks.* If you find yourself getting annoyed with Hacker News, take a break. Go for a walk, read a book, or do something else that you enjoy. Coming back to Hacker News with a fresh perspective can help you to avoid getting caught up in the negativity.

every single comment in this thread is exactly how I imagined commenting would go when Google eventually launched this product.

In the US and UK currently. Title should be modified IMHO

Can we talk for a moment about the name `Bard`? Is this really the best thing Google Marketing could come up with?

It's like they're not even trying anymore. SMH.

Still holding out for Google Fighter/Magic-User/Thief.

I wonder how long it’ll take before killedbygoogle.com adds bard to the list.

The point is, no one cares, google.

- you probably are behind OpenAI ChatGPT, and far behind GPT4 in the tool's quality

- people expect you to sunset the service soon either way, so no one starts to depend on it

- at this point you are a parasite that siphons from and killed the world wide web in the process

- your core value proposition (finding answers) is eaten up by the new chatbots that explain stuff instead of pointing to lists of ads and spam, most people don't care if its wrong sometimes

Well count down to when it will be eventually sunset

"Bard can explain why large language models might make mistakes"

Dat not so subtle passive aggressiveness, lol.

> Bard may display inaccurate or offensive information that doesn't represent Google's views

Yes, let's ship something to the general public that we know will go on racist tirades. It only took a few back and forth exchanges. Gonna pass on this one.

Ok, anyone who has access to Bard, can you tell me how it handles product reviews and recommendations? Does it actually do it like ChatGPT?

What I mean is that, is Google about to take a dump on people who've spent years writing reviews only to have their chat app do it directly from their interface?

If that is the case, a lot of people are about to go out of business.

From the NYT:

>This means the chatbot often gets facts wrong and sometimes makes up information without warning

Certainly this is the pot calling the kettle black.

> And it dovetails with Google’s index of all websites, so that it can instantly gain access to the latest information posted to the internet.

Is this true? If so then this would be a big advantage of Bard as it would be realtime-ish. I don't believe this to be true.

Reply on news.ycombinator.com