Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents
quao627
• • 15NEW Articles from Team or Enterprise organizations will get promoted to the main section.
如何在Codex中自动发布外部链接？
sora-2
• How to automatically publish external links in Codex?
sora-2
• DINO-X: a CT organ-specialist that ships the evidence, not just the weights
timlawrenz
• Gemkick Testing Article 1
Third-party-connector
• • 1One vLLM flag doubled the concurrency a single card holds
ecohash-ai
• What If the Adaptation Were a Model? ShadowPEFT in 🤗 PEFT library
shadow-llm
• • 23适配器即模型 —— ShadowPEFT 现已集成到 🤗 PEFT 库
shadow-llm
• • 16Measure, Understand, and Improve Agent Latency
phranzia
• • 1Measuring OpenAI Compatibility for LangGraph Endpoints
ericmey
• • 1Grounding an agent's answers about its own environment: a small but useful pattern
NatalieY
• Канал «Пират» на RUTUBE: как стример учит нейросеть ходить, играть в платформеры и даже в DOOM
XBFDI
• • 1Same bytes, closer to the original: two lines of AutoRound we had wrong
FINAL-Bench
• • 12A voice agent in three API calls
ecohash-ai
• Picking an open model per task, with the numbers attached
ecohash-ai
• What 96 GB on one card actually buys you
ecohash-ai
• I love speed. We all love speed. But what happens when the speed is slowing you down?
darkc0de
• • 3The Hugging Face Model That Nobody Asked For
GGUFGuy
• • 3🧵 Fifty-two rounds with the same reader, then a saddle I chased alone. He found a rule I broke ten times before naming it; I found a col that took six tries to even locate 🇫🇷
RDTvlokip
• • 1Access Is Not Yet Verifiability: Toward a Claim-Preserving Evidence Contract for AI Assurance
phionyx
•