Hacker News · AI·3d agoHow we made claude.ai 3x faster in two weeks#anthropic#claude#performance 9 sources 15 min
arXiv cs.CR·15d agoFresh-Challenge VDF Attestations for Model-Relative Response Latency#attestation#benchmark#cryptographyResearch
arXiv cs.AI / cs.LG / cs.CL·17d agoPACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving#cascading#inference-serving#latencyAI tools & infra
Help Net Security·Aug 14, 2026OpenAI’s GPT-5.6 Sol runs up to 14× faster with Ultrafast mode#api#cerebras#gpt-5.6
OpenAI News·Aug 13, 2026Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed#api#cerebras#gpt-5.6-solAI tools & infra