<- Back
Comments (40)
- 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
- status_quo69I'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?
- codethiefSounds like we're still on track for https://ai-2027.com, for better or for worse.
- 2001zhaozhaoPretty 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.
- jsemrauIf Apple's "Intelligence" paper has shown one thing is that never do something in the LLM that can also be done recursive and deterministic.
- dpwebThe discovery of some information theoretic limit to model learning (at least using current paradigms) can't come soon enough.
- mochacosine1206Wouldn’t it be funny if some other lab figures out RSI first and zooms past the biggies.
- woahThis sounds incredibly expensive
- throwyonionRock 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.
- anonundefined
- anonundefined
- mrkn1[dead]
- franzcoughka[dead]