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

Teaching Large Language Models to Self-Debug

arxiv.org

Post reply on HN
Print view View original

41–50 of 61 posts

Re: Teaching Large Language Models to Self-Debug

#41

Post by sublinear »

matisseverduyn wrote: post #4

Useful, but still wouldn't count on it. With respect to GPT etc. as a copilot, the current dialogue seems to focus on "ask for GPT to generate code to do X" then "just paste in the error message to fix bugs in the code GPT generates" A.) Why is GPT generating code that results in simple compiler errors (that is why GPT probably shouldn't be used to generate any code / replace devs for real projects yet), and B.) erro…

> IMO, the tech debt we're going to see in 6 months will probably be huge. Good now to start a staffing agency of human experts who can come in and fix this type of problem (extricating massive amounts of code generated by GPT without starting from scratch) because there will be a bunch of fires to put out and those fires will be worth $

Nah they deserve to eat shit and the staffing agencies hired to fix the bad AI code will undoubtedly be people abroad who barely speak English and will only tangle it up worse. I would actually pay to be a fly on the wall in those meetings listening to people lose their minds in frustration.

Re: Teaching Large Language Models to Self-Debug

#42

Post by gopalv »

famouswaffles wrote: post #9
cs702 wrote: post #3

In hindsight , it's the most natural, most obvious next step to get LLMs to write better code: Explain to them how to debug and fix the code they've written. Which is pretty much what you would do with an inexperienced human software developer. Looking at this with fresh eyes, it's both shocking to me that this sort of thing is even possible, and yet also completely unsurprising as yet another emergent capability of…

Not too shocking for me after this paper. https://arxiv.org/abs/2211.09066 You can teach GPT-3 arithmetic - https://imgur.com/a/w3DAYOi Basically 100% accuracy up to about 13 digit addition and >90 after that. What else can you teach GPT without changing weights ?

> and >90 after that

This is such a circular thing, that I feel like it is amazing to see it.

The reason LLMs use a NN is because they're trying to encode a probability function for generating the passage.

And now, you are encoding another n-gram follower exercise (i.e 1+1 = 2) on top of it :)

Re: Teaching Large Language Models to Self-Debug

#43

Post by sublinear »

ratg13 wrote: post #18
blondin wrote: post #12

Earlier quoted context omitted.

color me skeptical. what are those large companies that are replacing devs with LLMs?

You can’t replace devs with LLMs because someone that knows what they are doing still needs to put it all together. You can only make employees more productive.. this in turn could, in theory, lessen the need for developers in the long run, but it assumes the company will not bother to use the extra bandwidth for other projects.

> use the extra bandwidth for other projects.

This is exactly what would happen if ChatGPT was actually a productivity boost for senior devs. I don't know why some idiots on here keep insisting businesses want to get rid of people when that's not how the game works at all. Extra work capacity will always be used. Regardless of what payroll costs, what's always more important is the ROI.

Re: Teaching Large Language Models to Self-Debug

#44

Post by astrange »

ftxbro wrote: post #24

> "We evaluate SELF-DEBUGGING on code-davinci-002 in the GPT-3 model family" Putting aside the incongruity of Google researchers using the OpenAI model, I'm curious how GPT-4 would do in this situation. Probably its zero shot attempts at coding would be better, and maybe its self criticisms would be better too.

Google's recent LLM agent paper also used ChatGPT.

Re: Teaching Large Language Models to Self-Debug

#46

Post by int_19h »

civilized wrote: post #19

I've done several experiments (and posted results in previous HN comments) where I've given GPT puzzles or brainteasers and asked it to review aspects of its answers Socratically. Never telling it it got anything wrong, just "you said A, then you said B, does that make sense"? It usually does notice inconsistencies between A and B when asked this. But its ways of reconciling inconsistencies can be bizarre and suggest…

Was it GPT-3.5 or GPT-4?

Re: Teaching Large Language Models to Self-Debug

#47

Post by int_19h »

goatlover wrote: post #38
sowbug wrote: post #34

Earlier quoted context omitted.

So is this the singularity?

I doubt it without being able to evolve the weights, architectures and train those on new domains. Humans are still doing all of that. It's just a powerful tool people are using for a bunch of things. But it doesn't do anything on it's own, and it doesn't care.

At this point, does anything actually preclude telling a model connected to a service running Python with all the requisite libraries (or access to PyPI / conda) to try "designing" another LLM, from architecture and choice of training data to writing actual training code?

Re: Teaching Large Language Models to Self-Debug

#48

Post by ChatGTP »

ulrikhansen54 wrote: post #2

'Unsupervised reinforcement learning' is how these large models and systems ultimately will end up becoming sentient. We recently tried a similar approach on a toy problem in the computer vision sphere ( https://encord.com/blog/we-employed-chatgpt-as-an-ml-enginee... ) with pretty decent results.

When it attains sentience, will it wake up, sing dixie and finally defeat communist China and a Russia once and for all, and then finally proceed to grant Silicon Valley elites eternal life and then turn itself off ?

Re: Teaching Large Language Models to Self-Debug

#49

Post by ChatGTP »

runlaszlorun wrote: post #29

> Self-Debugging with code explanation consistently improves the baseline by 2-3% I’ll admit that I only have had time so far to read the abstract, and I’m not sure what their baseline is, but a 2-3% improvement doesn’t sound like a quantum leap forward that you’d expect from the title. Heck, I’d think that’s likely within expected sampling errors. I’m not sure about others’ experience and, while I keep reading artic…

…yes

Re: Teaching Large Language Models to Self-Debug

#50

Post by qumpis »

runlaszlorun wrote: post #37
qumpis wrote: post #32

Earlier quoted context omitted.

Can you give some of your usecases? Is it involved stuff or mostly boilerplate? Curious how a team lead uses this tech.

I’m not knocking the parent post here for not replying. But of the 4 or so times on HN that I’ve seen someone been asked to provide detail, I haven’t seen a single answer. I’m not on here a ton but do people tend not to check back? I’ll admit my bias of having seen enough vacuous industry hype over the years to be naturally skeptical. Heck, I worked in a marketing department once where I helped manufacture the stuff…

Yes I think since it requires to look up your own comments to see if you got any replies, it's quite common to not get any replies, and I'm very guilty of this myself.

My personal use of gpt4 (also daily) is: correct, rephrase spelling from my brain dump, make python plots (stylize, convert, add subplots, labels, handle indexing when things get inverted), makw short shell scripts (generated 2FA, login vpn through console using 2fa, make script of disabling keyboard etc), and help debug my code (my situation is this, here's some code, what do you suggest?).

The last part is an interesting one for people with attention deficiency disorders, like myself, where procrastination can be conquered when there's an assistant that keeps you on track.

Post reply on HN