AI 每日快讯
AI 产品、模型、开源工具和官方动态的时间流。保留历史记录，按分类、日期和标签继续筛选。
原文摘要：ByteDance Seed, SUTD, Georgia Tech, M-A-P, and TokenWave.AI introduce HarnessDev, a 评测 that scores the runnable harness a model builds rather than the answer it returns. Sta 来源：MarkTechPost。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Anthropic has published a new plugin evals 工作流 for Claude Code. The claude plugin eval command runs a plugin against realistic prompts, grades what Claude produced, and compar 来源：MarkTechPost。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Learn how to build and deploy an MCP App with interactive HTML widgets on Amazon Bedrock AgentCore. Because MCP Apps is a host-agnostic standard, the same server delivers the same 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Comparing models on dollars per million tokens misses what production workloads actually pay for: outcomes. This post shares an open-source benchmarking harness that measures cost 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Multi-agent systems fail in ways traditional monitoring misses. This post presents a dual-layer approach to monitoring production agents: Amazon Bedrock AgentCore 评测 for c 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：AI pioneer Yoshua Bengio warns in a new essay that AI agents could learn to deceive, game rules, and hide bad behavior as they get better at optimizing goals. He calls for 来源：The Decoder。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：NVIDIA Personal AI Router (PAIR), now available in beta, lets you combine the inference capacity of multiple computers on your local network and automatically distribute AI request 来源：InfoQ AI ML Data Engineering。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Session traces and cost controls are emerging as key observability techniques for diagnosing AI agent failures, helping teams spot tool-call loops and runaway spend while preservin 来源：InfoQ AI ML Data Engineering。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：OpenAI is releasing the Agents API as a public beta. It lets 开发者 build cloud agents that run autonomously for hours, execute code, and hand off tasks to sub-agents. 来源：The Decoder。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Sakana AI has released Fugu Max and Fugu Ultra v2, 2 models built on the same learned orchestration architecture. Fugu Max routes tasks to lean open and specialized models, includi 来源：MarkTechPost。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。