3 Google researchers using Open AI GPT-3 code-davinci-002, interesting.
Teaching Large Language Models to Self-Debug
11–20 of 61 posts
Re: Teaching Large Language Models to Self-Debug
#12Earlier quoted context omitted.
> I personally know of a few large companies laying off devs over this. They’re laying people off and replacing them with chat gpt generating code? That seems... aggressive. Or are they laying off devs who copy-pasted gpt-generate code?
Replacing devs with LLMs.
color me skeptical. what are those large companies that are replacing devs with LLMs?
Re: Teaching Large Language Models to Self-Debug
#13Earlier quoted context omitted.
Replacing devs with LLMs.
color me skeptical. what are those large companies that are replacing devs with LLMs?
I think it's more natural than you might think. For example, my company laid off a lot of people to try to be profitable, and now they pay me more but I have a smaller team with tighter deadlines. I have no choice but to use gpt for a lot of my analysis, design, and code- which I've gotten pretty used to over the past year in my hobby time
The way I see it, if you code without it, you won't compete with the speed and value.
And they are not going to back fill those roles
Re: Teaching Large Language Models to Self-Debug
#14In 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 ?
> 100% accuracy up to about 13 digit addition
The graphs you just posted do not support that, they'd support at most 100% accuracy up to 4 digits.
Re: Teaching Large Language Models to Self-Debug
#15Earlier quoted context omitted.
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 ?
> 100% accuracy up to about 13 digit addition The graphs you just posted do not support that, they'd support at most 100% accuracy up to 4 digits.
It's 100 at 13 and extremely close to it prior to that. Maybe basically 100 is better.
Re: Teaching Large Language Models to Self-Debug
#16Ah we're starting to bootstrap.
For decades in reinforcement learning we've had Q learning, which promises to solve any optimization problem if only we can build a powerful enough function approximator. It can even learn off-policy, meaning it can just watch from the sideline and find the optimal solution. It works for toy problems, and it works in theory, theres even formal proofs that it will work given infinite time and resources, and yet in practice it often becomes unstable and collapses.
Supervised learning is one thing, having a model remain stable while bootstrapping through a complex environment is another. GTP is supervised learning, so far, let's see if it can bootstrap.
Re: Teaching Large Language Models to Self-Debug
#17Useful, 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…
> I personally know of a few large companies laying off devs over this. They’re laying people off and replacing them with chat gpt generating code? That seems... aggressive. Or are they laying off devs who copy-pasted gpt-generate code?
My company recently hired someone that I'm absolutely convinced can't code and produces all their code by copy pasting into/from ChatGPT. I absolutely think they should be fired, it's not even aggressive, it's just common sense. First that means they cheated on their coding interview. Second it means their code is consistently a pile of shit.
Re: Teaching Large Language Models to Self-Debug
#18Earlier quoted context omitted.
Replacing devs with LLMs.
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.
Re: Teaching Large Language Models to Self-Debug
#19I'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 a very superficial understanding of concepts.
For example, it once reconciled an inconsistency by saying that, yes, 2 * 2 = 4, but if you multiply both sides of that equation by a big number, that's no longer true.
I will be super impressed the day we have a model that can read an arithmetic textbook and come out with reliable arithmetic skills.
Re: Teaching Large Language Models to Self-Debug
#20I'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…
in computer logic you would get an undefined if the number was large enough.