LLMs are not superhuman at reading and writing neural network weights

One could say they might be "superhuman" here in the same way that LLMs might be said to be superhuman at math. Perhaps they do this work faster and more effectively than any person could manually. But they are certainly still doing it the "human" way ie reasoning with legible and coherent thoughts, rather than communing through some Matrix-like symbology which is what people who skimmed the article seem to be assuming.

	▲	antonvs 13 hours ago \| parent [-]
		That "faster and more effectively" part is undeniably superhuman, and it can result in qualitative leaps in capabilities. For example, an LLM's ability to comprehend and explain a complex codebase, that it's never seen before, far outstrips that of any human. People like to come up with factors to quantify how much more efficient LLMs are. A newly hired human developer working on a complex codebase can take months to get up to speed, to get a holistic understanding of how it works so that they're able to make non-trivial changes. An LLM can do it in minutes. That's a factor on the order of 10,000x. It may not be "communing through some Matrix-like symbology," but at some point it starts to seem that way.

▲

StilesCrisis 4 hours ago | parent | prev | next [-]

"If someone showed you that heatmap without the game labels, I think you’d be able to immediately identify at least the first three games" -- absolutely not. Pac-Man in particular seems like a huge stretch to me.

▲

bradenlc an hour ago | parent [-]

Really? Pac-Man seemed easiest to me.

(One possible disconnect: each row in the grid is one game, so Pac-Man is the third row, not the third image.)

	▲	StilesCrisis an hour ago \| parent [-]
		Even watching the human-friendly animation I would have struggled to call it Pac-Man. You'd need to render the dots as dots and the ghosts as ghosts, then it'd be recognizable easily.

▲

solyin 4 hours ago | parent | prev | next [-]

> the best way to work with binaries is still to write source code and compile it. Likewise, the best way to update the weights of a model is to train it normally.

This is why the distinction between open weights and open source is important.

▲

nagi_builds 13 hours ago | parent | prev | next [-]

"I think a smart human ML researcher could perform all of these tasks."

And do that for how long?

	▲	simias 5 hours ago \| parent [-]
		That's not really the point of the article IMO. It's more about how there's nothing magical that happens when my calculator does 347987987 x 55998. I could do it by hand too if I wanted, even if I wouldn't be nearly as fast. Yes, the calculator can do it much faster, for much longer and much more reliably, but there's nothing surprising about that. The initial reporting/discussion surrounding these "LLMs understand LLM weights" made it sound as if these models had a superhuman ability to natively read and understand weights. Something that immediately seemed wild because I don't think that LLMs are trained to do that, so it would be an emergent ability. If you look at the details though, it's fairly standard reverse-engineering: identify unique traits of the machine code you're looking at and make educated guesses as to what the code does, then use this understanding to unravel the next bit of code etc...

▲

aaroninsf 2 hours ago | parent | prev | next [-]

False, in a way that genuinely matters.

True: they are superhuman at every one of these tasks, in the boring way they are better—according to a wall clock and the coupled standard of actual results—at other things, just not in some mystical way.

▲

lnenad 3 hours ago | parent | prev | next [-]

We keep moving the goalposts, I love it. A few years ago LLMs writing simple functions was downplayed and now this. I lovehate the future this will bring.

▲

aesthesia an hour ago | parent [-]

This isn't goalpost moving, it's pushing back against a misinterpretation of the paper's results (one that seems to have been encouraged by the authors).

	▲	lnenad 37 minutes ago \| parent [-]
		How is it pushing back, if anything it's mostly clarifying and the conclusion aligns with the original article: > It’s cool that Astra was able to make direct weight updates. But we shouldn’t think of this like a radically new capability that will change how AI research is done. We should think of this as analogous to the ability of LLMs to emit machine code and tweak compiled binaries: it’s an impressive trick, but the best way to work with binaries is still to write source code and compile it. It's like people are immediately forbidden to be impressed that AI was able to do this. The original article itself mentions the mechanisms by which Astra achieved this. They just of course wanted to gain more attention so they used a sensational title, like 90% of scientists that want their stuff read. How is it not moving goalposts, it knew how to detect which weights to update and a way to do it? Even this article says so in the part that I quoted. The original piece never stated humans are unable to do this, I don't even think it implied it. So being impressed with this accomplishment is actually ok.

▲

ChrisArchitect 16 hours ago | parent | prev | next [-]

Discussion on source:

https://news.ycombinator.com/item?id=50341174

▲

jiwidi 10 hours ago | parent | prev [-]

always one in the room