Teaching Large Language Models to Self-Debug
1–10 of 61 posts
Re: Teaching Large Language Models to Self-Debug
#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.
Re: Teaching Large Language Models to Self-Debug
#3In 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 LLMs.
We live in interesting times.
Re: Teaching Large Language Models to Self-Debug
#4Useful, 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.) error messages are (just guessing here) probably I personally know of a few large companies laying off devs over this.
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 $
Re: Teaching Large Language Models to Self-Debug
#5I'd be curious to know if having few-shot prompts that demonstrate making mistakes and then correcting them causes the model to make more initial mistakes so that it has something to correct.
Like as far as the model is concerned, how can it distinguish between the task being "do your best but if you do make an error, correct it" and "make some mistakes like in this example and then fix them".
Re: Teaching Large Language Models to Self-Debug
#6Useful, 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…
If an LLM hallucinates lines of code that can't even compile, I suppose it could also hallucinate logic issues which are more difficult to track down.
Re: Teaching Large Language Models to Self-Debug
#7Useful, 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…
If an LLM hallucinates lines of code that can't even compile, I suppose it could also hallucinate logic issues which are more difficult to track down.
Definitely. QA at a snails pace should still be the focus here for a while, but that's not what I'm observing in the real world. Just rush, pressure, layoffs. At least this sort of behavior keeps humans employed long-term.
Re: Teaching Large Language Models to Self-Debug
#8Useful, 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?
Re: Teaching Large Language Models to Self-Debug
#9In 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 ?
Re: Teaching Large Language Models to Self-Debug
#10Useful, 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?
Replacing devs with LLMs.