二〇二六年九月二十三日
收録 17 篇
- **Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization**
- jev-chat/jev-chat-jarvis
- The autonomous codebase
- SF October 14th: A Birds of a Feather Session on Agentic Engineering
- llm 0.36
- Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war
- Canary rollouts: upgrade models in production without downtime
- Quoting @therealcornpop
- Introducing GPT-6 Sol and Luna
- Better prompt caching for GPT-6
- Enabling Private High-Performance Production AI Inference with NVIDIA Confidential Computing
- Priorities and principles for effective third party assessments
- How UK AISI and EvalEval Are Making Benchmark Results Reproducible
- llm-typesafe 0.1a0
- GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
- RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
- Debating RSI, the US-China Gap, and Jaggedness with JS Denain of Epoch AI