The most complex model we actually understand
Welch Labs · 2 位 HN 用户推荐 · 2025–2026
Nice video o mechanical interpretability from Welch Labs: [link]
— lugu, 2025Astra and Fable are already hard to square with “mere autocomplete.” We may be (really) close to AGI, and token-by-token generation certainly doesn’t rule out subjective experience (I think we should at least treat that as an open question). Great videos: [link]
— mpodeley, 2026