On Tue, May 13, 2025 at 1:04 PM Rob Freeman <chaotic.langu...@gmail.com> wrote:
> BTW, while I'm commenting, YKY I understand you to be arguing that it > should be possible to learn a symbolic abstraction, and that it hasn't been > done because the learning needs a refactoring. Which strikes me as a > similar idea to startup Symbolica. George Morgan is working on graph > re-write rules of some kind. He had been working with Bruno Gavranović for > a category theoretic solution, but Morgan forced it back to graph > re-rewiting again. From what I understand. > My idea is not just "refactoring" but it's about making symbolic rules *differentiable*. I'm not aware of other people doing this so far... and so far I failed to make it work either... I just don't know if it is worth pursuing further 🫤 If their approach is purely symbolic I think it's a dead end also... YKY ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tdc5c19d0f38aacd6-M60c7d268143288d378e0c576 Delivery options: https://agi.topicbox.com/groups/agi/subscription
