Viewing profile — maxaravind

The blog discusses a potential path to making LLMs self-referential and self-directed continual learners. Solving continual learning is key to AGI - and we maybe close to solving i…

Didn't get this error before. Try now, it should be fixed.

I'd say the way to think about it is in terms of the questions you ask being in-distribution or out of distribution w.r.t the model training dataset. Consider this, if something fu…

There has been a lot of talk about how continual learning might be "just and engineering challenge" and that we could have agents that continuously learn from experience by just ha…

here you go: https://www.youtube.com/watch?v=Z0x99Uu4rJc

Nope. Even if context can theoretically encode arbitrary computation under fixed weights, this requires the weights to implement a usable interpreter. Random weights almost surely …

lol nice analogy. LLMs are frozen diamonds forged in compute. We need then to be malleable in production and change with experience.

I think both the views have their merits. In my mind the hardware vs software analogy for weights vs context holds better because in most modern computing systems, the hardware is …

Author here. I spent the last weekend thinking about continual learning. A lot of people think that we can solve long term memory and learning in LLMs by simply extending the conte…

One of the authors here. We ran this experiment a few weeks ago, but Anthropic’s Mythos report dropped this week and thought this would be relevant to share now. Surprisingly, we f…

The 1-2 files per request constraint is interesting. I do the same thing, but I've started thinking of it as a symptom rather than a solution. The reason you have to constrain scop…

Personal superintelligence sounds nice until you actually try to use it. We spent time yesterday arguing through an architecture decision. Today I ask the Agent to help implement i…

[dead]