thomasfromcdnjs

Thank you very much for writing this out!

I like the idea of this, will find something to run it on later.

Lot's of cynical answers.

I do think prompt engineering is a new industry, and your experience (if you actually good) will translate will into future jobs.

In my opinion it has to be combined with engineering to be competitive in a commercial sense.

I do the same, just tell Openai to call a parser at the end and wahal.

I love that it shows you the 90th percentile

I've always been fit but when I was in the office, I understood why a lot of people weren't. Work + Commute + Daily exercise is a HUGE chunk of time.

With remote, I simply exercise _during_ work with my home equipment, it's fantastic.

I personally would love a simple way to do a reverse proxy. It is not hard, but could be as easy as writing the hostname you want and what it points at.

Aha

Also thank you! I had an idea of how this all worked but this definitely concreted my thoughts.

I love when vegan studies always say that cows use X amount of water but their calculations never factor in that it rains.

---

I'd prefer when seeing these articles that the author talks about which land mass or eco system they are talking about.

Australia has hundreds of thousands of acres of land where the animals roam in self sustainable set ups.

Ripping up these ecosystems to grow nuts and beans would be "worse" for the environment.

I've also been using Twitter more since he bought it. I've been enjoying the promotion of long form videos, long form post, revenue sharing, paid accounts and at least an attempt at being more politically centrist.

Great answer btw.

And yes, that is what I meant. curl hackmeplease.com 57 stack traces down.

It would be nice to know if this vulnerability affects people who never made their Metabase installations publicly accessible.

Aka if I am running Metabase locally.

Thanks, one of those HN moments where I didn't read the original.

I lol'ed at a tweet the other day;

'“AI Alignment” is just a cancel culture for GPUs.'

https://twitter.com/tunguz/status/1681733141508046852

---

On a more quasi-serious note, surely no technically-modest person has a sincere idea on how to regulate LLM's or any GAN stuff et cetera for that matter.

If so, does it imply there is a potentiality for a black market?

I don't just re-heat my left overs, I make them into a new dish.

Defrosting is a funny one, most people don't know you can roast frozen chunks of meat perfectly fine.

You can reverse sear a frozen steak too. (it works, I've done it)

I sound like a tosser, but you know, food is one of the greatest things humans have to experience. (and perhaps the reason we exist at all)

Reading this thread, I didn't know so many people use microwaves.

I've never owned one, traditional cooking, food taste better and insert other conspiracies...

I'm not convinced that ones identity can be described as an introvert or extrovert. Regardless of what I read or what people I trust tell me.

I think you can _feel_ "introverted" or "extroverted" sometimes.

Not a topic that overly bother me, I personally find it hilarious watching people describe themselves with so much confidence. As if they know how the human mind works, and are so capable at it they can perform some meta-analysis looking from outside in.

(If you haven't figured I also think Meyers, Big Five etc etc is all garbage too, "I'm cynical" </joke>)

Someone should do a GPT analysis of HN submissions to find and catalogue the HN-Meta. The meta being, the general rise and fall of sentiments / curiosities.

I've been on here for 15 years and definitely feel phases when it seems like a lull because I am personally not interested in the current hype.

Side note: A few months ago, I swear I saw about 150 different databases I had never heard of on here.

I read the essays, intriguing history, rather difficult to digest, but changed my world view for the better.

It is mandatory reading — if you can't be bothered, just read the top five or ten.

> We've done this so much recently that I'm now seeing rewritten definitions of "real" intelligence that most humans do not meet.

Love this sentiment, stealing it =)

The video was quite nicely done (except the music)

I just have too much love for styled components.

I love naming things, it really helps you think about abstractions and guides you to reusability and more minimal design systems.

It probably depends where you are coming from, my day job generally involves building finicky complex UI's, Tailwind and other frameworks always just get in the way and look fugly by the end of implementation.

I don't have any example responses at hand here. But this was a prompt (that had a shitty pre-prompt of conversational messages) running on davinci-003.

https://raw.githubusercontent.com/thomasdavis/omega/master/s...

Had it hooked up to speech so you could just talk at it and it would talk back at you.

Gave incredible answers that ChatGPT just doesn't do at all.

The Chat-GPT models are all pre-prompted and pre-aligned. If you work with davinci-003, it will never say things like, "I am an OpenAI bot and am unable to work with your unethical request"

When using davinci the onus is on you to construct prompts (memories) which is fun and powerful.

====

97% of API usage might be because of ChatGPT's general appeal to the world. But I think they will be losing a part of the hacker/builder ethos if they drop things like davinci-003, which might suck for them in the long run. Consumers over developers.

I have this vague memory of a website where people could upload their bash scripts and more importantly a sort of primary setup script if you were booting up a fresh install.

The idea being after installing your distro, you could

> curl -sSL <script_url> | bash

It was somewhat of a social network. (10-20 years ago)

Am I taking crazy peoples or was this something...

I'd be curious to take a stab on your problem. I could arguably say it is simpler as it is just purely documented mathematics.

And/or you could use a prompt injection strategy to make sure it does have the available context to solve your problem.

e.g. a vector search for some text book snippet that gets injected in

3.5 or 4?

And did you also try the problem with Co-Pilot?

I'm a bit more open minded to what "reason" or our own understanding of our own "reason" might be.

I gave GPT-4 a bunch of code that had two regex functions to parse a given custom url. I also gave it in the same prompt an example of a url of what I wanted it to parse, and asked it to explain the code and tell me the answer.

It explained the code perfectly in moments and also gave me the correct answer.

Here was it's response -> https://pastebin.com/raw/CP9iZh7S

I would use this as an interview question, asking a junior dev to "reason" through the code, explain their thinking and without running it, tell me what they might think the answer would be. If I had to give them feedback for that answer, I would have commended their ability to "reason" about the problem. ¯\_(ツ)_/¯

(extra: The GPT-4 response knew to not bother with the second regex because it should only run the second if the first regex had a third part match, amazing...)

(side note: I can't wait until I can generate live documentation of every file in my code base)

What is the benefits of using the container kernel? Does alpine generally do this if it installed in a container?