HNHacker News
TopNewBestAskShowJobs

a1j9o94

74 karma · joined March 24, 2014

submissionscomments
a1j9o94··on GPT-5 is behind schedule
How do you even know what original sources to read?
a1j9o94··on GPT-5 is behind schedule
YouTube is such a great multimodal dataset—videos, auto-generated captions, and real engagement data all in one place. That’s a strong starting point for training, even before you filter for quality. Microsoft’s Phi-series models already show how focusing on smaller, high-quality datasets, like textbooks, can produce great results. You could totally imagine doing the same thing with YouTube by filtering for high-quality educational videos.

Down the line, I think models will start using video generation as part of how they “think.” Picture a version of GPT that works frame by frame—ask it to solve a geometry problem, and it generates a sequence of images to visualize the solution before responding. YouTube’s massive library of visual content could make something like that possible.

a1j9o94··on ChatGPT Pro
That's not necessarily true. There are many companies that have both end user products and B2 products they sell. There are a million specific use cases that OpenAI won't build specific products for.

Think Amazon that has both AWS and the retail business. There's a lot of value in providing both.

a1j9o94··on Launch HN: Human Layer (YC F24) – Human-in-the-Loop API for AI Systems
Yeah, exactly. You would define a HitL server and the actions it implements would be API calls to your system.
a1j9o94··on Amazon to invest another $4B in Anthropic
If you aren't using LLMs for most knowledge work you're probably wasting time somewhere.
a1j9o94··on Trump wins presidency for second time
I didn't say anything about Nazism in my comment.

Those are words Trump has used. He said the eating pets thing during the debate.

a1j9o94··on Trump wins presidency for second time
If you're looking for a quote of him saying that word for word, no. But it is not an unreasonable interpretation of the things he has said he wants to do. Especially when he's used language saying immigrants are "poisoning the blood of our country" and makes up lies about immigrants eating pets.

https://www.reuters.com/world/us/inside-trumps-plan-mass-dep...

a1j9o94··on Trump wins presidency for second time
How is ideological not wanting some level ethnic cleansing?
a1j9o94··on Trump wins presidency for second time
Agree. American's hate out groups and want to punish them. This just shows who people really are.
a1j9o94··on Trump wins presidency for second time
Harris' plan lowered taxes for everyone making less than 900K per year

https://itep.org/kamala-harris-donald-trump-tax-plans/

a1j9o94··on Trump wins presidency for second time
Inflation: "inflation has come down over the last two years, a lot of it has been from the healing of the supply side of the economy.

What is that? Supply chains have improved. The labor force has expanded, partly due to increased immigration, and that's helped to take some of the edge off of the supply-and-demand imbalances that we had when inflation was very high two years ago." https://www.pbs.org/newshour/show/examining-how-economic-pla...

Immigration: "After hitting a record high in December 2023, the numbers of migrants crossing the border has plummeted since then. Harris and the administration have credited their tough anti-asylum measures for stemming the flow, although increased enforcement on the Mexican side has also played a key role." https://www.ap.org/news-highlights/elections/2024/where-trum...

Abortion rights: "At one of her first campaign events, she stated that if Congress “passes a law to restore reproductive freedom, as president of the United States I will sign it into law.”" https://www.aclu.org/news/reproductive-freedom/how-kamala-ha...

If you don't like what her positions are that's your prerogative but it's just not true that she did not have answers to these questions.

a1j9o94··on Show HN: Supercharge Your Mac
I'll have to give this a shot. I switched from a windows machine to a Mac for a better dev experience on my personal projects, but I miss a lot of the windows file explorer shortcuts
a1j9o94··on Everything I built with Claude Artifacts this week
Not, the person you were replying to, but I think a better example of incrementally here would be

- write me a file with the function definitions for this problem. - compile that - write a test that test x outcome - compile that - then have it start writing functionality

If it's trying to one shot a complex problem that you would typically break up, your prompt is probably too vague.

a1j9o94··on Use Prolog to improve LLM's reasoning
I tried an experiment with this using a Prolog interpreter with GPT-4 to try to answer complex logic questions. I found that it was really difficult because the model didn't seem to know Prolog well enough to write a description of any complexity.

It seems like you used an interpreter in the loop which is likely to help. I'd also be interested to see how o1 would do in a task like this or if it even makes sense to use something like prolog if the models can backtrack during the "thinking" phase

a1j9o94··on How I animate 3Blue1Brown [video]
One example that comes to mind is Kahn academy. They've built out new pedagogical methods.

There's also Unacademy a company I'm sure has helped millions of people learn new things.

a1j9o94··on Upgrading Homebrew and avoiding the "failed to verify attestation" error
I ran in to the same problem last weekend and got this suggested fix from gpt-o1.

I did try to Google it first, but wasn't able to find anything on it.

a1j9o94··on Launch HN: Univerbal (YC W23) – Language learning with a conversational AI tutor
I had the same issue. I've been looking for good ways to learn Hindi.
a1j9o94··on The Richest Countries in 2023
In my anecdotal experience this hasn't been the case. Most people I know in the US can't afford to pay people to do house work or chores. I'm thinking in contrast to a place like India where it's the norm to have hired help for things like cooking, cleaning, and laundry.
a1j9o94··on Comparing humans, GPT-4, and GPT-4V on abstraction and reasoning tasks
Another thing I take issue with is this doesn't seem to be using known ways to improve performance of LLMs such as chain of thought and tree of thought prompting.
a1j9o94··on Prepare for a wave of US politicians to use AI in their campaigns
We're straight forward with voters that it's an AI

And we actually do have alerts that go to the campaign team if a voter asks something that the agent can't answer.

I don't see how it's anymore propaganda than having them hire a bunch of people to text you.

a1j9o94··on Prepare for a wave of US politicians to use AI in their campaigns
I'm currently building a company around using LLMs to communicate and understand voters. (https://colloqium.com)

My view here is a bit more optimistic. LLM will allow campaigns where each individual essentially has a personal outreach plan. It's like a candidate can have a personal conversation with every voter. This will make things less divisive because you can talk to each voter about things that matter to them. There's no need to say the most inflaming thing just to get engagement.

One other bonus is that smaller campaigns can get their message out in a way that's authentic to them. If you're a parent running for school board because you care about your child's education you don't have an army of volunteers to do the outreach for you.

a1j9o94··on MemGPT: Towards LLMs as Operating Systems
This is a fascinating approach! I posted this as a separate comment but would be curious about your response directly.

What do you think about the tradeoff of having an agent manage its own memory as opposed to having a separate agent whose job it is to manage the memory and the other agent just focuses on the conversation?

a1j9o94··on MemGPT – LLMs with self-editing memory for unbounded context
This is interesting. Can you expand on how this gets around the context window problem? Are you thinking the agent does a one-off task rather than continuing back and forth with the user?

I do think this will be way less than having all of the functions listed to begin with though. I think the discoverability is a novel approach. Honestly, I'm surprised ChatGPT with plugins doesn't do something like this by default rather than making you pick which plugins you want at the beginning of the conversation.

a1j9o94··on MemGPT – LLMs with self-editing memory for unbounded context
This is super interesting! I was thinking about how to approach a similar problem for a project I'm working on, and my approach is similar.

I am curious about the benefit of having the agent interact with the user (or doing the task) and managing its memory instead of having an observer agent that modifies the memory separately. The thought process is to let the agent use all of its tokens to focus on the task and not memory management.

a1j9o94··on XB, or eXtreme Bullshitting: a less misleading name for LLMs
I appreciate your perspective, but I have a slightly different view. First, it's important to recognize that the term "language model," as it's used in the context of machine learning, does not claim to fully capture the entirety of human language ability. Rather, it refers to a model's ability to predict or generate text that follows the patterns found in the language data on which it was trained.

You mention that a language model can't model language, only text, because it only observes examples of text, not language. However, I would argue that these text examples are in fact representations of human language ability. The text that language models are trained on is a product of human language ability. This text, while not a perfect representation of language, is a direct outcome of language use and thus carries within it the patterns and structures that language models can learn.

Moreover, models like Transformers do have a sort of latent space - the embeddings space. This is a continuous space where words and phrases are represented as vectors. The distances and directions between vectors in this space capture semantic and syntactic relationships, which suggests that these models are indeed learning some aspects of language, not just text.

On top of this, many of these models are trained on diverse data sources, including transcriptions of spoken conversations. This introduces elements of pragmatics, or how language is used in real-world conversations, into the training data.

Finally, the translation capabilities of these models further suggest that they are capturing something beyond mere text. They are able to translate between different languages, which implies that they are learning some underlying linguistic structures that are shared across languages.

Again, it's important to stress that these models are far from capturing the full complexity of human language ability. However, to say that they only model text and not language seems to me an oversimplification. They are learning patterns and structures in the data that are intrinsically tied to human language use, and so in a sense, they are modeling aspects of language.

a1j9o94··on ChatGPT conversations can be shared publicly
https://chat.openai.com/share/2ac75896-d0c7-4731-8519-3336f4...
a1j9o94··on Show HN: ModelMaster – Hands on excel training with in browser emulator
The premise here was to build a Codecademy style learning tool for excel.
← PreviousPage 2 of 2