co-sign. a very handy mental framework for what kinds of learning transformers do well today, and why it runs into limitations. when @ankit2…

co-sign. a very handy mental framework for what kinds of learning transformers do well today, and why it runs into limitations. when @ankit2119 and i wrote about the need for adversarial world models earlier this year, we were describing a couple of the functions of these rungs of thinking that bring us ever closer to the kolmogorov-limit generator of reality. throwing more params, more power, more everything at a demonstrably inefficient paradigm will be outclassed by the simple solution that can hypothesize and seek truth rather than backfit a house of cards - although the bitter lesson is it is simpler to scale and we may hit agi anyway because human intelligence just isn’t that smart nor plentiful Very well written blog. I think of RL as learning from interventions, and it kinda explains why it's more powerful as a paradigm than supervised learning. Now learning from counterfactuals is something we haven't been historically good at but maybe world modelling+ RL can get us …

Source: Swyx (X) | 2026-05-23