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

Self-Adapting Language Models

arxiv.org

Post reply on HN
Print view View original

61–70 of 81 posts

Re: Self-Adapting Language Models

#61

Post by throwaway314155 »

perrygeo wrote: post #60
fspeech wrote: post #59

Earlier quoted context omitted.

Reinforcement learning can be used to refine LLM as shown by Deepseek.

Everything I've read in the last 5 months says otherwise. Probably best described by the Apple ML group's paper call The Illusion of Thinking. It empirically works, but the explanation could just be that making the stochastic parrot squawk longer yields a better response. In any case, this is a far cry from what I was discussing. At best, this shows an ability for LLMs to "learn" within the context window, which shou…

> explanation could just be that making the stochastic parrot squawk longer yields a better response

No one in the research and science communities ever said anything contrary to this and if they did they wouldn't last long (although i imagine many of them would find issue with your stochastic parrot reference).

The apple paper has a stronger title than its actual premise. Basically they found that "thinking" definitely works but falls apart for problems of a certain difficulty and simply scaling "thinking" up doesn't help (for these harder problems)

It never said "thinking" doesnt work. People are just combining the title with their existing prejudices to draw the conclusion the _want_ to see.

Re: Self-Adapting Language Models

#63

Post by andai »

gavinray wrote: post #45

Two close friends of mine who were math prodigies that went on to do ML very early (mid 2010's) were always talking to me about an algorithm that sounds similar to this: "NEAT/HyperNEAT" (Neuroevolution of Augmented Topologies) [0] I'm no ML practictioner, but as I understood it, the primary difference between NEAT and what is described in this paper is that while NEAT evolves the topology of the network, this paper…

Here is my favorite introduction to NEAT:

SethBling's MarI/O - Machine Learning for Video Games

https://www.youtube.com/watch?v=qv6UVOQ0F44

Re: Self-Adapting Language Models

#64

Post by pton_xd »

khalic wrote: post #46

> Villalobos et al. [75] project that frontier LLMs will be trained on all publicly available human-generated text by 2028. We argue that this impending “data wall” will necessitate the adoption of synthetic data augmentation. Once web-scale corpora is exhausted, progress will hinge on a model’s capacity to generate its own high-utility training signal. A natural next step is to meta-train a dedicated SEAL synthetic-…

That's pretty much the state of today. Frontier LLMs are already trained on all publicly available human-generated text, and they are already heavily training on synthetic data to improve at verifiable tasks eg coding.

Re: Self-Adapting Language Models

#65

Post by pixl97 »

Davidzheng wrote: post #35
Centigonal wrote: post #21

It seems to me that "forgetting correctly" is rapidly becoming a more pertinent problem in this field than "learning correctly." We're making great strides in getting models to teach themselves new facts, but the state of the art in jettisoning the least relevant information given new knowledge and finite capacity is lagging far behind. "Forgetting correctly" is something most human brains are exceptionally good at,…

I don't think forgetting correctly is something humans are really good at. I'm not convinced human brains are "exceptionally good" at much of what we do tbh. I think human brain memory capacity is so large that most of forgetting is nowhere near "clearing space for new info" but because the brain correctly knows that some past bad information interferes with learning new things.

Eh, I'd disagree. First the human brain is an evolutionary miracle when it comes to filtering. When you walk in a new room and then are questioned about it later you will most likely remember things like the door or where set some object, but after that your brain will filter out and just make up details as needed.

The other thing is the brain down values and prunes paths we don't use and strengthens one's we do. This is why something you've not done it a while might need a refresher for you to do right again.

Re: Self-Adapting Language Models

#66

Post by maleldil »

notpushkin wrote: post #40
mackenziebowes wrote: post #36

Earlier quoted context omitted.

I can't be certain, I'm not at all an AI engineer or math guy, but I think at the "wake up" point you equalize instances. Like during 'sleep' some list of functions/operations `m` are applied to model weights `n` producing a new model, `n + 1`. Wouldn't you just clone `n + 1`, send it to work, and start a new training run `m + 1` to make `n + 2`?

This was my first idea as well. Keep training continuously and redeploy clones after each cycle. From a layman perspective this seems reasonable :thinking:

You can't realistically keep training the same model forever, or it will start forgetting things it knew before. The proper name for this is "catastrophic forgetting".

Re: Self-Adapting Language Models

#67

Post by cma »

Uninen wrote: post #50
cma wrote: post #6

From Anthropic a couple days ago too, self finetuning: https://arxiv.org/html/2506.10139v1

This is wild! "when assessed by Claude 3.5 Sonnet’s production-grade RM, our unsupervised assistant policy wins 60% of head-to-head comparisons against the policy trained with the human-supervised RM." So now the models can even post-train the new models better than a human can

Everytop model in ARC AGI used a test time finery king approach. They they had one example pair though and would usually do transformations (color, mirroring, etc) of it for the finetuning, and that might have been coded by hand

Re: Self-Adapting Language Models

#68

Post by Inviz »

johnsmith1840 wrote: post #24
libraryofbabel wrote: post #7

I wonder if anyone who’s really in the know could summarize where the research is at with getting LLMs to learn “on the job” (through continuous fine tuning or whatever) and what the blockers are to this being a useful deployable thing, e.g. having a model+coding agent that can actually learn a codebase over time (cost? model collapse? something else?). I’m sure this is something the big labs are trying but from the…

We have no idea how to do continual learning. Many people here are right, compute, collapse, forgetting whatever. The only "real" way to do this would be: 1. Train a model 2. New data 3. Retrain the model in full + new data 4. Repeat 5. You still have no garuntee on the "time" aspect though. But CL as a field basically has zero answers on how to do this in a true sense. It's crazy hard because the "solutions" are hyp…

Evolving prompts seems to fit the "modify without changing" bill, does it?

Re: Self-Adapting Language Models

#70

Post by zelphirkalt »

khalic wrote: post #47
gavinray wrote: post #45

Two close friends of mine who were math prodigies that went on to do ML very early (mid 2010's) were always talking to me about an algorithm that sounds similar to this: "NEAT/HyperNEAT" (Neuroevolution of Augmented Topologies) [0] I'm no ML practictioner, but as I understood it, the primary difference between NEAT and what is described in this paper is that while NEAT evolves the topology of the network, this paper…

Humans are amazing, we build a hypothetical computing system trying to understand neurons, then find out it’s not really how they do it, but whatever, we still build a paradigm shifting tech around it. And we’re still enhancing it with ideas from that imaginary system

Since we lack knowledge and means to build like the real thing, this is what we have to go on with for now. I think it is obvious, that the industry goes with whatever is available. Though all the uninformed hype of it by people thinking it works like the brain is certainly annoying.
Post reply on HN