LiquidAI tool-call adapters: up to 43% tool efficiency gain, 9 adapters with GGUFs
ariG23498 · x · 2026-11-09
Harness adapters for LiquidAI's LFM2.5-24B, LFM3, and Twil-8B have finished training, optimized for pi, hermes, and opencode. LFM3 gains up to 43% tool-call efficiency and 15% accuracy on a held-out data-analysis test set; Twil-8B gains up to 37% tool-call efficiency. Over 1900 RL steps were trained via Hugging Face Jobs, producing 9 ready-to-use adapters with GGUFs. A commenter likened the approach to "mega-kernels but for tool calls."
More from coding & agent
- Dev spins up thousands of computer-use agent VMs with live terminal streaming — wavefnx · 2026-11-10
- Cursor discloses tampered Claude Code extensions attempting persistent SSH backdoors — thione · 2026-11-10
- Perplexity CEO says Teammates usage grows daily, three updates ship this week — AravSrinivas · 2026-11-10
- feedthejim takes over ChatGPT/Codex Web & Desktop infra group at OpenAI — Dimillian · 2026-11-10
- Open-source Rewind for X extension logs every post you scroll past so refreshes stop losing good tweets — dotey · 2026-11-10
- "Just retry it" hides three LLM failure types — only one is fixed by retrying — ClickOk5811 · 2026-11-10