Mirendil launches Fern, a from-scratch pretrained model with up to 10M-token context
bneyshabur · x · 2026-10-26
Mirendil introduced Fern, its first model, pretrained from scratch with a context window of up to 10M tokens (23 MB of code) — enough to hold 0.5M lines of code (roughly Megatron-LM scale) or days of an agent's work in one context. Fern 0.1 ships after a short round of post-training, targeting whole-codebase understanding, long log debugging, and end-to-end agent trace reading.
Related event: Fern Team Argues 'Context Is Intelligence'; Debuts at 73.4 on SWE-Bench(4 posts)→
More from Models
- ARC Prize redesigns leaderboard: highest reasoning effort by default, CSV export — mhmazur · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27
- Rerunning Argon on Antigravity Harness lifts it past Astra, near Opus 5.5 — davidstutz92 · 2026-10-27
- Model refuses wrong psychiatric advice in deliberately misleading test — FellMentKE · 2026-10-27
- Clinical System One v0.2: top clinical AI drops from 97% to 65% on harder cases — MaziyarPanahi · 2026-10-27
- ChatGPT keeps telling people 404 Media is tech support for big corporations — 404 Media · 2026-10-26