Live data from Hacker News

Sparks of Artificial General Intelligence: Early Experiments with GPT-4

arxiv.org

151–160 of 244 posts

Re: Sparks of Artificial General Intelligence: Early Experiments with GPT-4

#151
post #22

Earlier quoted context omitted.

Our of curiosity, what is GPT-4 getting wrong so often? It’s prettily wild to my own , admittedly easily impressed, mind.

I've been trying to make it be a DM for a while now. It works seemingly well for a while but it's making everything up on the fly, which is fine as long as there's not state that needs to be maintained/remembered. Once you start trying to get it to do combat, it seems like it's working pretty well but eventually you realize that it's just making shit up behind the scenes. It'll tell you there are 4 goblins ambushing…

You should put a blog/site up with some examples.

"GPT being the worst DM ever" sounds hilarious.

"I attack the goblin." "What goblin?" "The goblin you just said was there." "I'm sorry, I was mistaken. It's actually a Beholder."

Re: Sparks of Artificial General Intelligence: Early Experiments with GPT-4

#152
post #110

I'm increasingly convinced you can build an agi system with gpt4. People are trying to get it to solve everything up front but I've had GPT3 do much better by taking it through a problem asking it questions. Then I realised it was good at asking those questions too so just hooked it up to talk to itself with different roles. Gpt4 seems much better overall and is very good at using tools if you just tell it how and wh…

I agree. There is something special about layering these guys. To me this is like we are looking at a static combustion engine without the vehicle. “How is this useful?” It’s that I’m not sure what the best approach is here. Waiting for other smarter folks to put the pieces together.

I'm taking the liberty to spread my most recent words of visionary wisdom here. (/s)

One of my main issues with these guys is their context window. Their memory. It's hard to see a LLM working on a code-base a few thousand tokens at a time and still being precise about it. To do that you need summary techniques. Feeding prompt with incrementally compressed summaries and hoping it will maintain cohesion.

That sounds a lot like trying to let the CEO of a company do all the grunt work by feeding him summaries. "Mr Gates, here's a 2 paragraph summary of our codebase. Should we name the class AnalogyWidgetProducer or FactoryWidgetAnalogyReporter?"

I don't think that's going to work.

My gut feeling is that what we call corporations are actually already a form of AI, but running on meat. I saw someone call Coca Cola a "paper clip maximizer", obviously for drinks instead of paper clips, but it actually - kind of - is. FWIW, I'm having a hard time thinking of it as anything else. Who controls it? What is it anyway?

CEOs have the same context window problem, which to my knowledge is mainly solved through delegation. The army might be another example. Generals, officers, privates. How do you expect a general to make sensible statements about nitty-gritty operational details? It is not possible, but that does not mean the system as-a-whole cannot make progress towards a goal.

Maybe we need to treat LLMs like employees inside a company (which in its totality is the AI, not the individual agents). If we have unfettered access to low-cost LLMs this might be easier to experiment with.

I'm thinking like spinning up an LLM for every "class" or even every "method" in your codebase and letting it be a representative of that and only that piece of code. You can even call it George and let it join in on meetings to talk about it. George needs some "management" too, so there you go. Soon you'll have a veritable army of systems ready to talk about your code from their point-of-view. Black box the son of a gun and you're done. Clippy 2.0. My body is ready.

Re: Sparks of Artificial General Intelligence: Early Experiments with GPT-4

#153
post #110

I'm increasingly convinced you can build an agi system with gpt4. People are trying to get it to solve everything up front but I've had GPT3 do much better by taking it through a problem asking it questions. Then I realised it was good at asking those questions too so just hooked it up to talk to itself with different roles. Gpt4 seems much better overall and is very good at using tools if you just tell it how and wh…

I am surprised by how many, even among the tech community, wholesale disregard GPT as a glorified auto-complete, or "a statistical model on human information". What, then, is the human brain if not a trained statistical model? Granted it is considerably more sophisticated in some ways, but in many other ways it is less sophisticated and less capable.

I wonder if the same reaction would have happened if ChatGPT had waited and released with GPT-4. It's very different.

Re: Sparks of Artificial General Intelligence: Early Experiments with GPT-4

#154
post #114
post #95

Earlier quoted context omitted.

That's fine. It's maybe not AGI IQ 180 to meet your demands but if we're honest it's pretty close.

Feynman had a really nice story about how he was into puzzles when he was at Princeton. It took him a while to solve the new ones, but eventually he learned all the well-known instances so he could answer instantly. It made him a genius in other people's eyes. All I want from AGI is to demonstrate that it can solve a straightforward logic problems (puzzles, if you will), that it provably didn't see before. Or at leas…

There's a 150-page paper solely to describe instances of it doing that. It's the article attached to this comment thread.

Re: Sparks of Artificial General Intelligence: Early Experiments with GPT-4

#155
post #14

ChatGPT and its relatives are very very impressive on first impressions, but I've been using ChatGPT-3 and now 4 heavily every day since they became available to individuals and once you start using them this much it becomes very clear how NOT intelligent they are. It really just seems like extremely impressive statistical inference after this much use and finding so many failure modes. But it is still impressive how…

Simple thought experiment: if I was a high school teacher and graded hundreds of exams, papers, and homework every month for years, would I develop the same opinion of my C-level students? The ones who have somewhat correct work, often inconsistent, clear that they're not thinking about the material, etc. Humans all start out like this, but as they grow they develop different masteries. Many of those masteries are ea…

So is Apple negotiating with some LLM mfr to integrate with realityOS ?

Re: Sparks of Artificial General Intelligence: Early Experiments with GPT-4

#156
post #14

ChatGPT and its relatives are very very impressive on first impressions, but I've been using ChatGPT-3 and now 4 heavily every day since they became available to individuals and once you start using them this much it becomes very clear how NOT intelligent they are. It really just seems like extremely impressive statistical inference after this much use and finding so many failure modes. But it is still impressive how…

It depends on 1) the domains 2) your comparison group. On 2), many software engineers and computer scientists compare these language models' logic and creative problem solving abilities with themselves and their peer group. But they are usually 1-2+ SD above average humans at these things. (Note: Someone gave GPT-4 an IQ test and the result was 96, slightly below the average of reference human group at 100. The SD of…

> Yes, GPT-4 is not an AGI yet, but the research paper (OP) has a point.

How did you go from "human-level IQ with some super-human abilities" to "not an AGI"?

Re: Sparks of Artificial General Intelligence: Early Experiments with GPT-4

#157
post #51

This is a pretty fluffy paper, especially for an institution like Microsoft Research. It says it's an "early AGI" in the abstract, but elsewhere says it's merely a "step towards AGI". The basis for this is asking ChatGPT a bunch of stuff, but they don't really present an overarching framework for what questions to ask or why. The paper makes outlandish claims like "GPT-4 has common sense grounding" on the basis of it…

> It's also the case that while GPT-4 can say a bear at the north pole is "white", it has no way of knowing what "white", or "bear", or "north" actually represent.

This is a preposterous claim that you could easily disprove within a few minutes of using it.

Re: Sparks of Artificial General Intelligence: Early Experiments with GPT-4

#158
post #114
post #95

Earlier quoted context omitted.

That's fine. It's maybe not AGI IQ 180 to meet your demands but if we're honest it's pretty close.

Feynman had a really nice story about how he was into puzzles when he was at Princeton. It took him a while to solve the new ones, but eventually he learned all the well-known instances so he could answer instantly. It made him a genius in other people's eyes. All I want from AGI is to demonstrate that it can solve a straightforward logic problems (puzzles, if you will), that it provably didn't see before. Or at leas…

The paper in question demonstrates it doing exactly this with varying success.

Re: Sparks of Artificial General Intelligence: Early Experiments with GPT-4

#159
post #83

I don't accept that something is AGI unless it can solve general instances of SAT (satisfiability problem, not the school test). Also recognizing (formulating from the task) an instance in the first place would help too. To me, these are hallmarks of reason, and not available in LLMs, in fact probably impossible just with pattern recognition.

can you solve general instances of SAT? can the average person?

Del Spooner getting offended panel

Re: Sparks of Artificial General Intelligence: Early Experiments with GPT-4

#160
post #68

I always thought General Intelligence would be Achieved by IBM or at least Apple, not by Microsoft. Now it will be used to pressure us into Windows Upgrades...

Rename ChatGPT to Clippy.

I wouldn't be surprised if they actually brought back Clippy as a character now that the technology's improved
Post reply on HN