新智元 (微信公众号)T2·78 pts
- Claude Opus 5.5 independently built an inference engine with Claude Code under no-internet, 12-hour, four-GPU constraints
- In 16-way concurrent coding-session replay, P90 time-to-first-token fell from about 12s on SGLang to roughly 0.48s
- Singularity-Bench turns 'can agents build agents' into a quantifiable, reproducible benchmark task