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

OpenAI is good at unminifying code

glama.ai

Post reply on HN
Print view View original

271–280 of 321 posts

Re: OpenAI is good at unminifying code

#271

Post by 015a »

lifthrasiir wrote: post #23

JS minification is fairly mechanical and comparably simple, so the inversion should be relatively easy. It would be of course tedious enough to be manually done in general, but transformations themselves are fairly limited so it is possible to read them only with some notes to track mangled identifiers. A more general unminification or unobfuscation still seems to be an open problem. I wrote handful of programs that…

The act of reducing the length of variable names by replacing something descriptive (like "timeFactor") with something much shorter ("i") may be mechanical and simple, but it is destructive and reversing that is not relatively easy; in fact, its impossible to do without a fairly sophisticated understanding of what the code does. That's what the LLM did for this; which isn't exactly surprising, but it is cool; being so immediately dismissive isn't cool.

Re: OpenAI is good at unminifying code

#272

Post by dontlikeyoueith »

ninetyninenine wrote: post #234

This is an example of superior intellectual performance to humans. There’s no denying it. This task is intellectual. Does not involve rote memorization. There are not tons and tons of data pairs on the web of minimized code and unminified code for llms to learn from. The llm understands what it is unminifying and it is in general superior to humans on this regard. But only in this specific subject.

Yes, bow down before your god.

You people are so weird.

Re: OpenAI is good at unminifying code

#273

Post by dontlikeyoueith »

fenomas wrote: post #169
mjburgess wrote: post #119

Earlier quoted context omitted.

Sure, but that claim wouldn't be true for humans, right? So it's a nonsequiteur. The relevant claim would be: all humans can do is move around in their environments, adapt the world around them through action, observe using adaptive sensory motor systems, grow and adapt their brains and bodies in response to novel and changing environments, abstract sensory motor techniques into symbolic concepts, vocalize this using…

> all they can do is, in fact, sample from a compression of historical texts To me, results like the Othello paper make any sort of "stochastic parrot" thinking completely untenable. https://thegradient.pub/othello/

That's because you don't understand what you're reading.

Re: OpenAI is good at unminifying code

#274

Post by visarga »

mjburgess wrote: post #119
stavros wrote: post #49

Earlier quoted context omitted.

I see your point, but I think there's more to it. It's kind of like saying "all humans can do is perceive and produce sound, any other ability is just a side-effect". We might be focusing too much on their mechanism for "perception" and overlooking other capabilities they've developed.

Sure, but that claim wouldn't be true for humans, right? So it's a nonsequiteur. The relevant claim would be: all humans can do is move around in their environments, adapt the world around them through action, observe using adaptive sensory motor systems, grow and adapt their brains and bodies in response to novel and changing environments, abstract sensory motor techniques into symbolic concepts, vocalize this using…

> In the case of transformers all they can do is, in fact, sample from a compression of historical texts using a weighted probability metric.

You seem to think LLMs operate independently from humans. That doesn't happen in practice. We prompt LLMs, they don't just sample at random. We teach them new skills, share media and stories with them, work, learn and play together. It's not LLMs alone. They are pulled outside their training distribution by the user. The user brings their own unique life experience into the interaction.

Re: OpenAI is good at unminifying code

#277

Post by xanderlewis »

sitkack wrote: post #195
xanderlewis wrote: post #29

Earlier quoted context omitted.

It’s not only their core strength — it’s what transformers were designed to do and, arguably, it’s all they can do. Any other supposed ability to reason or even retain knowledge (rather than simply regurgitate text without ‘understanding’ its intended meaning) is just a side effect of this superhuman ability.

Hinton claims they do reason. I am going to go with Hinton on this.

Hinton's opinions on LLMs are frankly bonkers. Just because you're famous — and intelligent and successful — doesn't mean you can't be completely wrong.

Also: what's his rationale? It's no use simply claiming something without evidence. And as far as I (and seemingly most others) can see, there's no such evidence other than that they can sometimes output sentences that happen to be true. But so can Wikipedia — does that mean Wikipedia is reasoning?

Also, any form of reasoning in the usual sense of the word would surely require the ability to allocate arbitrary amounts of computation (i.e. thought) to each question. LLMs don't do this — they don't sit and ponder; each token takes exactly the same amount of computation to produce. Once they hit an 'end of text' token, they're done.

Even empirically speaking, LLMs' ability to reason can be seen to be nonexistent. Just try asking basic mathematics questions. As soon as you ask anything for which the answer isn't available — practically verbatim — on the web already, it produces intelligent-sounding gibberish.

This whole idea that 'LLMs must be able to reason because in order to learn to fake reasoning you must learn to actually reason' is like some kind of inverted no true Scotsman fallacy.

Re: OpenAI is good at unminifying code

#279

Post by anticensor »

jehna1 wrote: post #97

Author of HumanifyJS here! I've created specifically a LLM based tool for this, which uses LLMs on AST level to guarantee that the code keeps working after the unminification step: https://github.com/jehna/humanify

Thanks for creating this megafier, can you add support for local LLMs?
Post reply on HN