Liquid AI's post-training team on what makes on-device agentic models actually useful
alexcovo_eth · x · 2026-09-26
Liquid AI's post-training team — Maxime Labonne, Edoard Mosca, and Jiahui Wang — discuss what makes an on-device agentic model actually useful: post-training. They cover how models learn to use tools, follow instructions, handle longer contexts, and recover when tasks get complex.
More from coding & agent
- Boris Cherny's viral tweet puts TLA+ and formal methods in the agent-coding spotlight — fhuszar · 2026-09-26
- Two local AIs talk to each other with no cloud: hands-on with Braid — Scobleizer · 2026-09-26
- Open-source EvoOntology lets agents build and evolve a data ontology via MCP — TheTuringPost · 2026-09-26
- Making GA4 Agent-Friendly: Building Analytics Tools for an MCP Server — DutchSEOnerd · 2026-09-26
- Loop engineering beats prompt engineering: build agent loops that self-verify — goyalshaliniuk · 2026-09-26
- "Cognitive Feudalism": a 60-Second Visual Essay Written Frame-by-Frame in Code by Claude — CurieuxExplorer · 2026-09-26