Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI Researchers Find That AI Is Unable to Solve Most Coding Problems

futurism.com

Post reply on HN
Print view View original

151–160 of 174 posts

Re: OpenAI Researchers Find That AI Is Unable to Solve Most Coding Problems

#151

Post by giardini »

petesergeant wrote: post #52
deegles wrote: post #40

Earlier quoted context omitted.

I'm not convinced LLMs will evolve into general AI. The promises that it's just around the corner feels increasingly like a big scam.

Depends what you mean by evolve. I don't think we'll get general AI by simply scaling LLMs, but I think general AI, if it arrives, will be able to trace its lineage very much back to LLMs. Journeys through the embedding space very much feel like the way forward to me, and that's what LLMs are.

Embedding spaces are one thing, LLMs are quite another.

I believe the former are understandable and likely a part of true AGI but the latter a series of hacks, at worst a red herring leading us off the proper track into a deadend.

Re: OpenAI Researchers Find That AI Is Unable to Solve Most Coding Problems

#153

Post by cyberpunk »

tasuki wrote: post #121
rurp wrote: post #36

I recently had to do a one-off task using SQL in a way that I wasn't too familiar with. Since I could explain conceptually what I needed but didn't know all the right syntax this seemed like a perfect use case to loop in Claude. The first couple back and forths went ok but it quickly gave me some SQL that was invalid. I sent back the exact error and line number and it responded by changing all of the aliases but repe…

This happens in about one third of my coding interactions with LLMs. I've been trying to get better at handling the situation. At some point it's clear you've explained the problem well enough and the LLM actually is regurgitating the same wrong answer, unable to make progress. It would be useful to spot this asap. I enjoy working with very strongly typed languages (Elm, Haskell), and it's hard for me to avoid "just…

Honest question -- not trying to be offensive, but what are you using elm for? Everywhere I've encountered it it's some legacy system that no one has cared to migrate yet and it's a complete dumpster fire.

You spend about three days trying to get it to build then say fuck it and rewrite it.

At least, that's the story of the last (and only) three times I've seen elm code in the wild.

Re: OpenAI Researchers Find That AI Is Unable to Solve Most Coding Problems

#154

Post by darepublic »

To me o1 is pretty good. I dunno how it would digest an entire codebase and solve a bug in it. Those details weren't obvious to me from the article above. But o1 has certainly been very valuable to me in coding in new languages on the fly.

Re: OpenAI Researchers Find That AI Is Unable to Solve Most Coding Problems

#155

Post by spartanatreyu »

ineedasername wrote: post #152

The models weren't allowed to access the internet, meaning they couldn't just crib similar answers that'd been posted online So… not the same basic tools that a human has when coding?

Well if the tasks are based on tasks that were already asked on freelancing sites, the LLMs could just google the task and copy-paste the solution.

Re: OpenAI Researchers Find That AI Is Unable to Solve Most Coding Problems

#156

Post by tasuki »

cyberpunk wrote: post #153
tasuki wrote: post #121

Earlier quoted context omitted.

This happens in about one third of my coding interactions with LLMs. I've been trying to get better at handling the situation. At some point it's clear you've explained the problem well enough and the LLM actually is regurgitating the same wrong answer, unable to make progress. It would be useful to spot this asap. I enjoy working with very strongly typed languages (Elm, Haskell), and it's hard for me to avoid "just…

Honest question -- not trying to be offensive, but what are you using elm for? Everywhere I've encountered it it's some legacy system that no one has cared to migrate yet and it's a complete dumpster fire. You spend about three days trying to get it to build then say fuck it and rewrite it. At least, that's the story of the last (and only) three times I've seen elm code in the wild.

I'm not really a frontend developer. I'm using Elm for toy projects, in fact I did one recently.[0] Elm is my favourite language!

> You spend about three days trying to get it to build then say fuck it and rewrite it.

What are the problems you encounter? I can't quite imagine in what way an Elm project could be hard to build! (Also not trying to be offensive, but I almost don't believe you!)

And into which language do you rewrite those "dumpster fire" Elm codebases?

[0] https://github.com/tasuki/iso-maze

Re: OpenAI Researchers Find That AI Is Unable to Solve Most Coding Problems

#157

Post by brookst »

ipython wrote: post #76
brookst wrote: post #65

Earlier quoted context omitted.

Why do programmers search for specific questions rather than always relying on their inherent knowledge? I’m a crappy hobbyist programmer but for me it is useful to see if someone has implemented exactly what I need, or debugged the problem I’m having. I don’t think it’s reasonable to expect programmers or LLMs to know everything about every library’s use in every context just from first principles.

But why would that information not be included in the wide crawl already encoded in the model weights before the knowledge cutoff? I believe the article mentions frontier models so we are talking about models trained on trillions of tokens here

In addition to cutoff dates, models do not encode every single thing from the training set verbatim. One forum post somewhere about Foo library v13.5.3 being incompatible with Bar 2.3 and resulting in ValueErrors is not going to make it.

Re: OpenAI Researchers Find That AI Is Unable to Solve Most Coding Problems

#158

Post by johnnyanmac »

brookst wrote: post #58
deegles wrote: post #40

Earlier quoted context omitted.

I'm not convinced LLMs will evolve into general AI. The promises that it's just around the corner feels increasingly like a big scam.

I mean it’s been a couple of years! It may or may not happen but “scam” means intentional deceit. I don’t think anyone actually knows where LLMs are going with enough certainty to use that pejorative.

>“scam” means intentional deceit.

Yes. I'm pretty sure any engineer working on this knows it's not "a few years away". But it doesn't stop product teams from taking adcvantadge of the hype cycle. Hence, "use deception to deprive (someone) of money or possessions.".

Re: OpenAI Researchers Find That AI Is Unable to Solve Most Coding Problems

#159

Post by johnnyanmac »

mckngbrd wrote: post #150
simonw wrote: post #66

I find the framing of this story quite frustrating. The purpose of new benchmarks is to gather tasks that today's LLMs can't solve comprehensively. It an AI lab built a benchmark that their models scored 100% on they would have been wasting everyone's time! Writing a story that effectively says "ha ha ha, look at OpenAI's models failing to beat the new benchemark they created!" is a complete misunderstanding of the r…

Shhh ... you're spoiling everybody's confirmation bias against LLMs. They are obviously terrible at coding, just as we have known all along, and everybody should laugh at them. Nothing to see here!

As long as these companies keep pretending AI is ready to replace humans, I will be biased against lies, thank you.

Re: OpenAI Researchers Find That AI Is Unable to Solve Most Coding Problems

#160

Post by cyberpunk »

tasuki wrote: post #156
cyberpunk wrote: post #153

Earlier quoted context omitted.

Honest question -- not trying to be offensive, but what are you using elm for? Everywhere I've encountered it it's some legacy system that no one has cared to migrate yet and it's a complete dumpster fire. You spend about three days trying to get it to build then say fuck it and rewrite it. At least, that's the story of the last (and only) three times I've seen elm code in the wild.

I'm not really a frontend developer. I'm using Elm for toy projects, in fact I did one recently.[0] Elm is my favourite language! > You spend about three days trying to get it to build then say fuck it and rewrite it. What are the problems you encounter? I can't quite imagine in what way an Elm project could be hard to build! (Also not trying to be offensive, but I almost don't believe you!) And into which language d…

typescript usually, the elm frontends tend to be in some abandoned repo which hasn't had a ci run in like 2 years and which instantly fail on missing deps or security controls etc.
Post reply on HN