LFM2.5-24B LoRA adapters for Pi and Claude Code cut tool calls by up to 40%
yb2698 · x · 2026-10-30
Liquid AI released LoRA adapters trained on top of LFM2.5-24B for open-source agentic harnesses like Pi and Claude Code. The recipe: take a strong model, train a LoRA adapter with TRL + OpenEnv to use fewer tool calls — on Pi the adapters achieve the same success rate with roughly 39% fewer tool calls, up to 40% reduction.
Related event: LFM2.5-24B Harness Adapters Cut Tool Calls ~39% via LoRA+RL(6 posts)→
More from coding & agent
- Data leakage hit 648 papers across 30 fields; autoarxiv now auto-reproduces arXiv papers — pandeyparul · 2026-10-30
- METR trial: AI made experienced devs 19% slower while they felt 20% faster — srimisra · 2026-10-30
- Clairvoyance: free desktop tool wires Claude Code, Codex and other agents into your daily workflow — draginol · 2026-10-30
- Same Prompt, Same Data: Claude's Fabric App Beats Its Dashboard at One-Fifth the Cost — adnan_hashmi · 2026-10-30
- Antigravity's Google Slides Plugin Audits an 80-Slide Deck Against Docs — rseroter · 2026-10-30
- OpenAI hosts Cloud Native Hackathon Nov 9; hack turns M5Stack into a k8s desk pager — OpenAIDevs · 2026-10-30