Dev Praises DeepSeek's Eval Harness: 'They Really Cooked'
mariofilhoml · x · 2026-11-05
Developer mariofilhoml tweets praise for DeepSeek's eval harness, saying the team 'really cooked with their harness' — a positive community signal on the quality of DeepSeek's benchmarking setup.
More from Models
- ThursdAI podcast roundup: AI edits AI, 948 Linux bugs, Kimi K3.1 weights — thursdai_pod · 2026-11-06
- Dev complains Claude Code quality has tanked: same models, shockingly worse results — IanArawjo · 2026-11-06
- Cryptographer Matthew Green: can abliterated GLM write 0days? Just test it — matthew_d_green · 2026-11-06
- Astra refusals decoded: safety training fires at the local level, not against safety research — thebasepoint · 2026-11-06
- Tencent releases Hy4 with vision and computer use, claims second place among Chinese AI models — The Decoder · 2026-11-06
- Developer: GPT 6.1 is far less creative than Opus 5.5, taste must be spelled out — zsakib_ · 2026-11-06