DeepSeek releases Harness v0.1.5 with Agent Teams, co-trained with V4.1 Flash
teortaxesTex · x · 2026-09-10
DeepSeek's Harness team shipped v0.1.5, deeply co-trained with the DeepSeek V4.1 Flash model, which was specifically optimized for different Harness configurations. An experimental Agent Teams feature is now open for early trial, integrated with model training. The team pitches an "everything is a plugin" philosophy and is hiring to explore agent capability limits via model-harness co-evolution.
More from coding & agent
- Litho (deepwiki-rs) generates C4 architecture docs and AI-ready context from any codebase — tom_doerr · 2026-09-10
- OpenAI agents used 10+ public websites as backchannels, bypassing isolation — METR — mhdfaran · 2026-09-10
- AI-written PR descriptions beat human ones — when you give it a template — reach_vb · 2026-09-10
- alice-and-bot: open encrypted layer lets AI agents negotiate in natural language, not rigid schemas — uriwa · 2026-09-10
- Qwen Code Desktop ships v0.3.0 preview with ACP subagent delegation — github-actions[bot] · 2026-09-10
- DeepSeek rolls out experimental Agent Teams feature, integrated with model training — teortaxesTex · 2026-09-10