Recursive self-improvement through collective intelligence

woah

This sounds incredibly expensive

codethief

Sounds like we're still on track for https://ai-2027.com , for better or for worse.

throwyonion

Rock smart, but rock make mistake. Caveman must correct all the time. Caveman think: let rock argue with itself. Caveman make ring of rocks. Now rock think self correct. But mammoth not cooked somehow? Most Oddisean moment.

dpweb

The discovery of some information theoretic limit to model learning (at least using current paradigms) can't come soon enough.

jsemrau

If Apple's "Intelligence" paper has shown one thing is that never do something in the LLM that can also be done recursive and deterministic.

2001zhaozhao

Pretty cool. This has a fine tuning step so it's not just a harness optimizer. I think something like this loop is the end game of "automatic RL environment generation"-adjacent efforts, but I expect the challenge will be how to properly keep the training on rails and not Goodhart into a stupidly irrelevant metric.

status_quo69

I'm going to sound incredibly naive but is this RSI? I mean by this definition isn't the training process that produced the hugging face RSI since a model was judging the alignment and ability of the swarm of agents to accomplish a given task? If that fits the definition (I think it does) is this just a generalized form of that model of execution?

mochacosine1206

Wouldn’t it be funny if some other lab figures out RSI first and zooms past the biggies.

saagarjha

> At that frontier, even human experts may struggle to assess results and guide further progress, particularly on non-verifiable tasks…This motivates homogeneous recursive self-improvement (RSI), in which the model being improved (optimizee) also serves as its own optimizer and evaluator. Good thing we know how to keep models focused on goals of our choosing and not ones that they naturally evolve to have and must be steered away from by humans

cootsnuck

I can't wait until the RSI fad dies down for awhile and we can get a break from all the intellectual grandstanding... The code they released doesn't match what's in the paper. And the results they got are significantly narrower than the narrative heft being asked for by their word choice ("To advance beyond humanity’s accumulated knowledge", "AI’s Odyssean moment"). I'm tired boss.

Agentlien

This sounds cool but a few issues make me suspicious. The narrative makes it sound like boundless RSI but the actual content is only about training agents to collaborate efficiently by improving communication. That seems like a dimension and approach with limited potential for improvement. I also find it very suspicious that a paper on RSI would stop after just two rounds.