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

131–140 of 174 posts

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

#131

Post by threatofrain »

whilenot-dev wrote: post #96
jameslk wrote: post #68

Earlier quoted context omitted.

I had to do something similar with BigQuery and some open source datasets recently. I had bad results with Claude as you mentioned. It kept hallucinating parts of the docs for the open datasets, coming up with nonsense columns. Not fixing errors when presented the error text and more context. I had a similar outcome with 4o. But I tried the same with o1 and it was much better consistently, with full generations of qu…

> and provided bits of the docs. At this point I'd ask myself whether I want my original problem solved or if I just want the LLM to succeed with my requested task.

That depends on how hard it is to auto ingest context.

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

#132

Post by casey2 »

"Here's the choice you have when you are faced with something new. You can take this technological advance and decide "This is a better way of doing the stuff I'm doing now and I can use this to continue on the path that I'm going", so that's staying in the pink plane , or you can say "This is not a better old thing, this is almost a new thing and I wonder what that new thing is trying to be" and if you do that there's a chance of actually perhaps gaining some incredible leverage over simply optimizing something that can't be optimized very much. - Kay

Current LLMs will change the world, but it won't be by completing pull requests quickly.

Although a "stargate level" LLM could accelerate pink plane traversal so much that you don't even need to find the correct usecase. LLM scaling will be the computer graphics scaling of this generation. In terms of intelligence gpt4 based o3 is but a postage stamp. As LLMs scale a picture of intelligence will emerge.

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

#133

Post by ai-christianson »

ripped_britches wrote: post #69
tkgally wrote: post #56

Earlier quoted context omitted.

> unless non-SWE people using LLMs become technical enough to get what they need out of them Non-SWE person here. In the past year I've been able to use LLMs to do several tasks for which I previously would have paid a freelancer on Fiverr. The most complex one, done last spring, involved writing a Python program that I ran on Google Colab to grab the OCR transcriptions of dozens of 19th-century books off the Interne…

This is a good anecdote but most software engineering is not scripting. It’s getting waist (or neck) deep in a large codebase and many intricacies. That being said I’m very bullish on AI being able to handle more and more of this very soon. Cursor definitely does a great job giving us a taste of cross codebase understanding.

> This is a good anecdote but most software engineering is not scripting. It’s getting waist (or neck) deep in a large codebase and many intricacies.

The agent I'm working on (RA.Aid) handles this by crawling and researching the codebase before doing any work. I ended up making the first version precisely because I was working on a larger monorepo project with lots of files, backend, api layer, app, etc.

So I think the LLMs can do it, but only if techniques are used to allow it to hone in on the specific information in a codebase that is relevant to a particular change.

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

#134

Post by jr-ai-interview »

pton_xd wrote: post #8

Well, OpenAI does currently have 288 job openings, including plenty of software engineers, so that says something.

Lol, that place is causing so many worldwide horrors misrepresenting AI I would't give sama an answer to an email at this point.

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

#136

Post by ldjkfkdsjnv »

tsimionescu wrote: post #82
ldjkfkdsjnv wrote: post #30

I’ve got 15 years of coding experience at some of the biggest tech companies. My personal opinion is that most people have no clue how good these AI coding systems already are. If you use something like RepoPrompt, where you selectively choose which files to include in the prompt, and then also provide a clear description of what changes you want to make—along with a significant portion of the source code—a model lik…

Are you suggesting that OpenAI published a paper assessing their own models on real-world problems, but failed to properly use their own models? And/or that you know better than OpenAI scientists how to use OpenAI models most effectively?

thou shall not question the high priests

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

#137

Post by halis »

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…

While I do find llm’s useful, it’s mostly for simple and repetitive tasks.

In my opinion, they aren’t actually coding anything and have no amount of understanding. They are simply advanced at searching things and pasting back an answer that they scraped online. They can also run simple transformations on those snippets like rename variables. But if you tell it there’s a problem, it doesn’t try to actually solve the problem. It just traverses to the same branch in the tree and tries to give you another similar solution in the tree or if there’s nothing better it will give you the same solution but maybe run a transformation on it.

So, in short, learn how to code or teach your kids how to code. Because going forward, I think it’s going to be more valuable than ever.

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

#138

Post by tsimionescu »

ldjkfkdsjnv wrote: post #136
tsimionescu wrote: post #82

Earlier quoted context omitted.

Are you suggesting that OpenAI published a paper assessing their own models on real-world problems, but failed to properly use their own models? And/or that you know better than OpenAI scientists how to use OpenAI models most effectively?

thou shall not question the high priests

That's not what I'm saying.

But telling us that the designers of a product are stupid and don't know how to use their own product when they're disclosing its limitations should really come with more than a "trust me bro" as evidence.

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

#139

Post by AbstractH24 »

Increasingly I think that the impact of generative AI is going to more of an incremental form of disruption than revolutionary. More like spreadsheets than the printing press.

Spreadsheets becoming mainstream made it easy to do computing that once took a lot of manual human labor quite quickly. And it made plenty of jobs and people who do them obsolete. But they didn’t upend society fundamentally or the need for intelligence and they didn’t get rolled out overnight.

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

#140

Post by AbstractH24 »

halis wrote: post #137
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…

While I do find llm’s useful, it’s mostly for simple and repetitive tasks. In my opinion, they aren’t actually coding anything and have no amount of understanding. They are simply advanced at searching things and pasting back an answer that they scraped online. They can also run simple transformations on those snippets like rename variables. But if you tell it there’s a problem, it doesn’t try to actually solve the p…

> So, in short, learn how to code or teach your kids how to code. Because going forward, I think it’s going to be more valuable than ever.

Teach your kids how to be resourceful and curious. Coding is just a means to an end to do that. Agreed though it’s a great one.

Post reply on HN