Cohere ML Summer School: Building First Agentic Models for Edge Devices
Cohere · youtube · 2026-07-30
Cohere officially previewed its 2026 ML Summer School, featuring a keynote by Maxime Labonne on building the first agentic models for edge devices.
Current agentic models are mostly cloud-based, raising concerns over cost, privacy, and latency. The talk will explore how to post-train frontier models into tiny, reliable phone-native agents using:
- On-policy preference alignment
- Agentic reinforcement learning
- Curriculum training with iterative model merging
More from coding & agent
- 'LLM code is sloppy' rebutted with real ffmpeg code: identical if/else branches in a top library — kingslyj · 2026-10-16
- Office-editing tool calls need file, worktree and unit: lessons from dsh-univer-office — FunDistribution6537 · 2026-10-16
- Architect MD workflow: Gemini one-shot outputs that beat Opus, via 5-lens plan critique — oikk01 · 2026-10-16
- Prove a coding agent actually ran the tests: check artifacts, not approvals — ComprehensiveShake76 · 2026-10-16
- Building an acceptance harness for AI spreadsheet edits: allowlists, recalc checks, idempotency — ukdicha-modakkk · 2026-10-16
- Agent actions need checks outside the model: NVIDIA demos lean on guardrails amid wave of real agent incidents — Creamy-And-Crowded · 2026-10-16