Delve Town's 'bee' model was further trained by Claude for ~24 hours
Sauers_ · x · 2026-10-13
Developer Sauers shares that the 'bee' model on Delve Town was further trained by Claude for about 24 hours starting from the original checkpoint, with the author personally paying inference costs so the model can reply to users.
More from Models
- Anthropic says new defenses cut distillation-harvested data by 90-99%, names Zhipu's GLM-5.3 — scaling01 · 2026-10-13
- Anthropic says it cut distiller data harvesting by 90-99%, turning away trillions of tokens — abhiadesai · 2026-10-13
- Ex-exMVP: post-training should add a facet for how well models explain things — MParakhin · 2026-10-13
- GLM-5.3 abliterated for a month, no takeover: dev rails against AI doom narratives — mariofilhoml · 2026-10-13
- Claude auto-files a bug report about itself: TLDRs still too long after user asked for shorter — andrey_kurenkov · 2026-10-13
- BridgeBench one-prompt test shows Muse Wonder is fast and cheap but worst-looking — PVORY · 2026-10-13