FRAMEWIREIndonesiaUpdated Sep 29Live wire
0:00 / 0:00

Local AI DeepSeek Harness shipped Agent Teams and it's quietly the biggest multi-agent drop in a while.

A shared task board where named AI agents collaborate and message each other — and the model itself can spawn + coordinate its own teammates.

DizzzankSep 29
0:00 / 0:00

US companies are not using Claude or Codex.

Too expensive. They run on Quen, DeepSeek, and Kimi instead. My move: use Opus as the orchestrator, then let it delegate work to cheaper models. Cheap tokens, same output.

Jonathan Acuña - Doctor AISep 29
0:00 / 0:00

I don't know if this will be helpful to anyone, but I did something quite special when creating #DeepSeek-chan this time.

By making multiple references to both the original image and the see-through image, we succeeded in having GPT generate a single part with high image quality while inferring the back of the part. Well, there are some mistakes.

AI開発@LinkHUBのお兄さんSep 29
0:00 / 0:00

The first build of Qwen3.8-Flash IQ3_XXS had bugs.

DeepSeek V4.1 Flash tried 5 times 20 minustes and couldn't fix them—but Qwen3.8-Flash IQ3_XXS fixed them in the second build. For coding, Qwen is definitely better.

unbugSep 29