DeepSeek rolls out experimental Agent Teams feature, integrated with model training
teortaxesTex · x · 2026-09-10
DeepSeek users spotted a new experimental "Agent Teams" feature, with official messaging saying it is "deeply integrated with model training" and inviting early trials.
Observers noted DeepSeek already had subagents but this feels subtly different, likening it to Tachikoma-style swarm intelligence — and pointing out it took only about 9 hours from concept to rollout.
More from coding & agent
- OpenClaw demos multiplayer cloud sessions playing Minesweeper on remote AWS — vincent_koc · 2026-09-10
- ai-engineering-from-scratch: 523 structured lessons on building AI systems hits 53.9k stars — tom_doerr · 2026-09-10
- Google Engineers Open-Source Mantis, a Toolkit for Agents That Find and Patch Vulnerabilities — Saboo_Shubham_ · 2026-09-10
- Dev uses GPT-6 plus custom music theory skill library to reimagine Timberlake and Zelda tunes as Bach, Liszt — doodlestein · 2026-09-10
- 10 open-source projects for securing AI agent skills, plus what they all miss — bibryam · 2026-09-10
- Dev shares workflow: build in C++/OpenGL first, then have latest models port it to web — gandamu_ml · 2026-09-10