Mirendil debuts Fern, a from-scratch model with up to 10M token context built for agentic AI R&D
shayan_ · x · 2026-10-27
Startup Mirendil introduced Fern 0.1, its first model, pretrained from scratch with up to 10 million tokens of context — roughly 0.5M lines of code or days of agent work in context at once. It targets high-volume agentic work in AI R&D: auditing training data, debugging runs from logs, and reading agent traces end to end. The company says next-token prediction keeps improving as context grows to 10M; Fern is the smallest of three models, with two larger ones now pretraining.
Related event: Mirendil Launches Fern 0.1, a From-Scratch Model with 10M-Token Context(7 posts)→
More from coding & agent
- SF 'Code Engineering' event picks up where 1,000-person harness engineering meetup left off — LangChain · 2026-10-27
- Prompt turns Claude Code into an iPhone backup forensics tool exposing 30-day 'deleted' photo copies — alex_verem · 2026-10-27
- Prompt turns Claude Code into a forensics tool finding deleted iPhone photos in backups — alex_verem · 2026-10-27
- Phones won't be mobile IDEs but control planes for agent fleets, argues Yuchen Jin — Yuchenj_UW · 2026-10-27
- FrontierCS 2 launches on Kaggle: 48 tasks make agents beat published CS papers — MeganRisdal · 2026-10-27
- Agent Field Kit launches $29 security runbooks for production AI agents — alvelda · 2026-10-27