Thread

1. ssddanbrown · 1790685372 · focus · HN ↗

   RSI here is for "recursive self-improvement", instead of a harness being built to help users with repetitive strain injury like I first thought when reading the post title

   1. broodbucket · 1790687724 · focus · HN ↗

      We gotta do something about these clashing TLAs.

      1. polotics · 1790691177 · focus · HN ↗

         Well for starters the use of the term "Recursive" is very dubious.

         This is as far as the eye can see all very iterative, there is no tail-call or anything fancy, it is loops. Also "Recursive" I feel kind of tries to imply the LLM's weights are being pushed around in some feedback, because to recurse you have to invoke the thing you're recursing into at its very start right? That would be reinforcement probably, and there is none of that in any such RSI so far, at least not public. Please someone contradict me with examples.

         So please: "ISI" for iterative self improvement is fine. Also "ISI" does not fit the (outdated!) Vernon Vinge "singularity" trope, and that is a good thing!

         1. IanCal · 1790692314 · focus · HN ↗

            I'm unsure.

            The example in the docs of improving nanochat is iterative. It's a looped process in one thing altering a second thing.

            What would be recursive is raven updating raven to make it better at doing things. For what I picture as RSI the important part would be that it's able to make itself better at doing things and better at improving itself.

            Now there's an "evolver" part that improves the harness over time but I don't know how far that goes or what scope it has to update things.

            I guess it's that if you have a function called "optimise" that takes functions and makes them better, calling optimise(my_process) is iterative regardless of how many times you do it. Calling optimise(optimise) is inherently different.

Unofficial Hacker News client; not affiliated with Y Combinator.