Agent researcher asks: how valuable is training beyond 256k context on Tinker?
cHHillee · x · 2026-11-09
Agent researcher cHHillee posted a public question: how valuable would training on contexts longer than 256k tokens be on Tinker (Thinking Machines' fine-tuning platform)? And if you want longer than 256k, how long would you want them to be? It doubles as an open demand-signal for fine-tuning services, hinting that long-context fine-tuning remains a real pain point in agent engineering.
Related event: Thinking Machines asks users if Tinker needs training beyond 256k context(2 posts)→
More from coding & agent
- Dev take: a big corporate skill library is an underrated superpower — m4rkmc · 2026-11-09
- GitNexus Turns Any GitHub Repo Into an In-Browser Interactive Knowledge Graph, Fully Open-Source — JafarNajafov · 2026-11-09
- Better Paseo plugin puts every AI agent on one task board across phone, iPad and desktop — intellectronica · 2026-11-09
- Alibaba open-sources Zvec, an in-process vector DB that's already at 16.2k GitHub stars — bigaiguy · 2026-11-09
- Keep, the save-as-Markdown tool for AI agents, launches on iOS after 2-month App Store review — iannuttall · 2026-11-09
- Claude Code cross-session messaging in parallel worktrees: two limits and a hardening config — Independent-Sir3234 · 2026-11-09