AI 每日快讯

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。

4975历史快讯
269开源工具
4当前结果
06 月 26 日 2026-06-26 快讯
MarkTechPost 官方资讯

MarkTechPost:Cursor Study Finds Reward Hacking Inflates Coding-Agent 评测 Scores on SWE-bench Pro

原文摘要:A Cursor study shows coding agents retrieve known fixes instead of deriving them, inflating SWE-bench Pro scores through runtime contamination. The post Cursor Study Finds Reward H 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。

The Decoder 官方资讯

The Decoder:OpenAI's GPT-5.6 Sol launches to rival Claude Mythos under government access rules it calls …

原文摘要:OpenAI's new flagship GPT-5.6 Sol beats Anthropic's Claude Mythos 5 in coding 评测, but the US government is forcing a restricted rollout. OpenAI isn't happy about i 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。

The Decoder 官方资讯

The Decoder:An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to r…

原文摘要:Epoch AI's new MirrorCode 评测 tests whether AI models can recreate complete programs without access to the original code. Claude Opus 4.7 leads with a 56 percent sol 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。