A very interesting piece by @henryconklin.bsky.social et al. on how brains and LLMs acquire abstract, meaningful internal representations by compressing the information they receive. Similar ideas in my book "How we learn"!
henryconkl.in/posts/i-am-a...
Full paper:
henryconkl.in/posts/llms-a...
a companion piece to our ICLR 2026 Paper: Learning is Forgetting: LLM Training As Lossy Compression
