FRAMEWIREIndonesiaUpdated Aug 17Live wire
0:00 / 0:00

Harness has some of the best observability UI out there - just this feature is an LLM model debugger

It is as important as the "developer" tab in Chrome. Great taste, tianyi and the DeepSeek team!

leozcAug 175
0:00 / 0:00

2.02 minutes. That's the time-to-train for DeepSeek-V3 671B on 8,192 NVIDIA GB300 NVL72 GPUs in MLPerf®…

2.02 minutes. That's the time-to-train for DeepSeek-V3 671B on 8,192 NVIDIA GB300 NVL72 GPUs in MLPerf® Training v6.0, the fastest result in the round on this benchmark. Our new whitepaper covers the engineering behind the number.

CoreWeaveAug 1725
0:00 / 0:00

And using DeepSeek harness with the pro v4 took it to next level.

MaverickAug 171
0:00 / 0:00

DeepSeek just open-sourced an agent runtime that can call Claude Code and Codex as sub-agents inside its own sessions.

DeepSeek Harness isn't hype — here's why it actually matters. This breakdown goes past the surface-level launch coverage and digs into what DeepSeek Harness

Lomash KumarAug 174