Harness launches live LoRA RL training on LFM2.5, LFM3 and Twil-9B for agent tasks
omarsar0 · x · 2026-11-07
HackClub's Harness adapters training is now live: using reinforcement learning to train LoRA adapters that make open models more efficient and accurate on agentic tasks.
Models being trained include LFM2.5 / LFM3 from Liquid AI and the recent Twil-9B from Twil (thewebAI). The training runs are public and can be followed live.
More from coding & agent
- Trail of Bits: Three Lessons From Running Hundreds of AI Agents on Critical OSS — banteg · 2026-11-07
- Theory Ventures hosts AI agent hackathon: 5 hours to run the most profitable bakery in town — HamelHusain · 2026-11-07
- Theo on T3 Code positioning: know exactly who your product is actually for — IsForAt · 2026-11-07
- Google study: devs expect agents to perform as-is while juniors grow via review — rseroter · 2026-11-07
- Indie dev builds a pipeline that only drafts posts when something actually ships — petrusenko_max · 2026-11-07
- Build vs rent an LLM: own your company's brain — memory, decisions and data first — petrusenko_max · 2026-11-07