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

Embarrassingly simple self-distillation improves code generation

arxiv.org

Post reply on HN
Print view View original

91–100 of 227 posts

Re: Embarrassingly simple self-distillation improves code generation

#91

Post by zug_zug »

an0malous wrote: post #47

I’d like to understand AI research better and I recall some posts a while back where someone collected all the key papers that one should read, but I don’t remember enough to be able to find it. Does anyone know what I’m talking about and could link me to that post?

This might sound paradoxical -- but any decent LLM will be happy to explain all the papers to you at great depth, and read new ones, and translate the math into simpler concepts and such. It'll also happily recommend relevant math to study, or give training problems, or whatever you want.

Re: Embarrassingly simple self-distillation improves code generation

#92

Post by user_7832 »

bensyverson wrote: post #50
user_7832 wrote: post #40

Earlier quoted context omitted.

> I love that we're still learning the emergent properties of LLMs! TBH, this is (very much my opinion btw) the least surprising thing. LLMs (and especially their emergent properties) are still black boxes. Humans have been studying the human brain for millenia, and we are barely better at predicting how humans work (or for eg to what extent free will is a thing). Hell, emergent properties of traffic was not understo…

Learning about the emergent properties of these black boxes is not surprising, but it's also not daily. I think every new insight is worth celebrating.

Oh I very much agree that it's great to see more research and findings and improvements in this field. I'm just a little puzzled by GP's tone (which suggested that it isn't completely expected to find new things about LLMs, a few years in).

Re: Embarrassingly simple self-distillation improves code generation

#93

Post by jameshart »

vova_hn2 wrote: post #89
bensyverson wrote: post #16

Really fascinating how this works; it's basically context-aware decoding. From the paper: > Code interleaves fork positions, where several continuations are genuinely plausible and may correspond to different solution approaches, with lock positions, where syntax and semantics leave little ambiguity but a low-probability distractor tail still remains… The best global decoding setting is therefore necessarily a compro…

I've always thought that it is kinda weird that we spend exactly the same amount of compute to calculate both "fork" tokens and "lock" tokens. I think that with grammar-aware sampling / constrained decoding [0][1] it is possible to sometimes skip calling the model altogether if only one token is allowed by grammar and just insert it, but I don't think that any of the current, widely used combinations of models/harnes…

Give coding agents access to intellisense and syntax highlighting.

Making coding agents spit out syntactically correct code token by token is like asking a human to code on a whiteboard.

Re: Embarrassingly simple self-distillation improves code generation

#94

Post by zug_zug »

vishnugupta wrote: post #33

Can someone please eli5 this to a friend web developer? I read the abstract but couldn’t understand much.

ELI 5

You teach the machine by asking it to solve some problems, and then whatever answer it gives you say "That's exactly right. Now we train on those answers YOU just gave me" (even if they are wrong) and repeat. Somehow THAT works over time.

Re: Embarrassingly simple self-distillation improves code generation

#95

Post by user_7832 »

Invictus0 wrote: post #69
user_7832 wrote: post #40

Earlier quoted context omitted.

> I love that we're still learning the emergent properties of LLMs! TBH, this is (very much my opinion btw) the least surprising thing. LLMs (and especially their emergent properties) are still black boxes. Humans have been studying the human brain for millenia, and we are barely better at predicting how humans work (or for eg to what extent free will is a thing). Hell, emergent properties of traffic was not understo…

To say we've been studying the brain for millennia is an extreme exaggeration. Modern neuroscience is only about 50 years old.

I hate to "umm, akshually" but apparently we have been studying the brain for thousands of years. I wasn't talking about purely modern neuroscience (which ironically for our topic of emergence, (often till recently/still in most places) treats the brain as the sum of its parts - be them neurons or neurotransmitters).

> The earliest reference to the brain occurs in the Edwin Smith Surgical Papyrus, written in the 17th century BC.

I was actually thinking of ancient greeks when writing my comment, but I suppose Egyptians have even older records than them.

From https://en.wikipedia.org/wiki/History_of_neuroscience

Re: Embarrassingly simple self-distillation improves code generation

#96

Post by bensyverson »

user_7832 wrote: post #92
bensyverson wrote: post #50

Earlier quoted context omitted.

Learning about the emergent properties of these black boxes is not surprising, but it's also not daily. I think every new insight is worth celebrating.

Oh I very much agree that it's great to see more research and findings and improvements in this field. I'm just a little puzzled by GP's tone (which suggested that it isn't completely expected to find new things about LLMs, a few years in).

I'm the GP! lol… Not sure how you got that from my tone, but I find these discoveries expected but not routine, and also interesting.

Re: Embarrassingly simple self-distillation improves code generation

#97

Post by jwolfe »

jameshart wrote: post #93
vova_hn2 wrote: post #89

Earlier quoted context omitted.

I've always thought that it is kinda weird that we spend exactly the same amount of compute to calculate both "fork" tokens and "lock" tokens. I think that with grammar-aware sampling / constrained decoding [0][1] it is possible to sometimes skip calling the model altogether if only one token is allowed by grammar and just insert it, but I don't think that any of the current, widely used combinations of models/harnes…

Give coding agents access to intellisense and syntax highlighting. Making coding agents spit out syntactically correct code token by token is like asking a human to code on a whiteboard.

In general these agents support LSPs, which is often as much information as your IDE will give you. They are also not required to output syntactically correct code token by token when running agentically, because the loop is:

1. code

2. syntax check / build / format / lint (details language dependent)

3. test

and they can hop between 1 and 2 however many times they want.

Re: Embarrassingly simple self-distillation improves code generation

#98

Post by sgbeal »

jameshart wrote: post #93
vova_hn2 wrote: post #89

Earlier quoted context omitted.

I've always thought that it is kinda weird that we spend exactly the same amount of compute to calculate both "fork" tokens and "lock" tokens. I think that with grammar-aware sampling / constrained decoding [0][1] it is possible to sometimes skip calling the model altogether if only one token is allowed by grammar and just insert it, but I don't think that any of the current, widely used combinations of models/harnes…

Give coding agents access to intellisense and syntax highlighting. Making coding agents spit out syntactically correct code token by token is like asking a human to code on a whiteboard.

> Give coding agents access to intellisense and syntax highlighting.

i once asked an LLM if it could ingest code from an interactive session more easily if it were in appropriately-typed markdown fences and it said absolutely yes, and that the syntax highlighting fed to it that way helps it immensely. i was downright shocked that syntax highlighting was anything more than noise for them.

Re: Embarrassingly simple self-distillation improves code generation

#99

Post by zer00eyz »

amelius wrote: post #80
zer00eyz wrote: post #76

Earlier quoted context omitted.

The intersection of physics isnt psychology it is philosophy, and the same is true (at present) with LLM's Much as Diogenes mocked Platos definition of a man with a plucked chicken, LLM's revealed what "real" ai would require: contigous learning. That isnt to diminish the power of LLM's (the are useful) but that limitation is a fairly hard one to over come if true AGI is your goal.

What do you mean by the intersection of physics? The intersection of what with physics?

The intersection of disciplines.

Sir Roger Penrose, on quantum consciousness (and there is some regret on his part here) -- OR -- Jacob Barandes for a much more current thinking on this sort of intersectional exploratory thinking.

Re: Embarrassingly simple self-distillation improves code generation

#100

Post by vova_hn2 »

jameshart wrote: post #93
vova_hn2 wrote: post #89

Earlier quoted context omitted.

I've always thought that it is kinda weird that we spend exactly the same amount of compute to calculate both "fork" tokens and "lock" tokens. I think that with grammar-aware sampling / constrained decoding [0][1] it is possible to sometimes skip calling the model altogether if only one token is allowed by grammar and just insert it, but I don't think that any of the current, widely used combinations of models/harnes…

Give coding agents access to intellisense and syntax highlighting. Making coding agents spit out syntactically correct code token by token is like asking a human to code on a whiteboard.

Yeah, I was also thinking about it A LOT.

We kinda have a little bit of it with some coding harnesses giving model access to LSP, but I think that we can insert this knowledge on a lower level if we find a clever way to somehow utilize it during sampling.

I think that there is a lot of low hanging fruit in this area.

And in general, I think that people try to use LLMs too much to solve problems that can be easily solved by cheaper (computationally), and, more importantly deterministic tools.

For example, back in the day when LLM-assisted coding just became a thing people very often complained about models generating syntactically incorrect code and inventing non-existent library methods.

Well, I, an experienced human programmer, probably would also be making syntax mistakes and inventing non-existent methods if you stripped me of my tools and made me write code in a bare text editor without syntax highlighting.

Thankfully, my IDE would autocomplete real syntax and actually existing library methods for me and immediately give me feedback if I make a mistake anyway. And all of it is achieved using reliable deterministic code without the inherent issues of statistical models.

I think that it is really inefficient to reach for an expensive and unreliable tool when a cheap and reliable tool will do.

Post reply on HN