Mirendil debuts Fern, a from-scratch model with up to 10M-token context built for AI R&D agents
shayan_ · x · 2026-10-27
Mirendil introduced Fern 0.1, its first model pretrained from scratch with a context window of up to 10 million tokens — roughly 0.5M lines of code or days of agent work in context at once. The company says next-token prediction keeps improving as context grows to 10M tokens.
Fern targets high-volume agentic work in AI R&D: auditing training data, debugging training runs from logs, and reading agent traces end to end. Fern 0.1 is Mirendil-Base after a short post-training round, the first and smallest of three models — two larger ones are now being pretrained, with frequent updates and model availability promised soon.
Related event: Mirendil Debuts Fern, a From-Scratch Model with 10M-Token Context(12 posts)→
More from coding & agent
- BELL: Open-Source Stack Combines Browserbase, Eve, iMessage and Stripe Link for Personal Agents — jeff_weinstein · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27
- Two engineers rebuilt a FedEx supplier's billing core in 3.5 months vs an estimated 7-8 — alex_verem · 2026-10-27
- GPT-6.1 Terra scores 48 on AA Coding Agent Index at one-third the cost of GPT-5.6 Terra — ArtificialAnlys · 2026-10-27
- Shift-1 router cuts coding agent spend up to 55% while keeping SWE-bench accuracy — ypatil125 · 2026-10-27
- Non-coder vibe-codes a Godot JRPG with Claude Code in two weeks, music and art synced — ADHDavid · 2026-10-27