最新资讯
dev.to 精简 MCP server 工具数量:更少工具、更小影响面,双重收益 dev.to 为什么 git checkout 无法撤销 AI 编码 agent 的改动? wechat AI短剧门槛降降降!实测即梦短剧工作室:剧本分镜预演一条龙,伙伴计划长期护航 dev.to 让模型改写文档前,先量化事实保真度 dev.to 回放 153 个 Claude Code 与 Codex 会话,审计 Agent 的生产影响范围 dev.to 银行 77 意图分类最便宜 LLM:GPT-6.1 Terra 每次成功任务 $0.000727 theinformation.com Chesky的副业:Airbnb向CEO新设AI实验室出售IP theverge.com OpenAI 宣布数据中心项目不再与公职人员签署保密协议 dev.to NVIDIA 发布四个开放 Cosmos 3 仿真模型 dev.to 真实 MCP 客户端击穿我们服务器的五种方式 theverge.com Airbnb 正在开发 AI 旅行 agent,计划 2027 年上半年推出 wechat 这可能是美国AI最魔幻的一天。
多元动态
登录 注册
行业动态 x.com · @a16z

a16z播客:AI评估的独立性与成本挑战

原文 我的收藏

a16z与Vals AI CEO讨论AI评估,指出模型能力多自我报告,公共基准易饱和,需独立持续评估,并探讨地缘政治和成本问题。

AI推荐理由 a16z播客讨论AI评估重要性,引用Vals AI CEO观点,涉及基准饱和、独立评估等话题,但为观点分享,非具体产品发布。

75 浏览 18,542 点赞 69 评论 15 转发 11

正文

Vals AI co-founder and CEO Rayan Krishnan with a16z's Ben Horowitz and Jennifer Li on grading AI, what it costs, and who gets to make the rules: Every big industry eventually grows an independent testing layer. AI has credit ratings to learn from and Enron to avoid. Model capability today is still mostly self-reported. As public benchmarks saturate and models get better at optimizing for the tests themselves, Rayan makes the case for independent, continuously evolving evaluations. The harder problem is geopolitical. Reagan's "trust but verify" worked during the Cold War because you could fly over and count the missiles. No simple equivalent for AI models exists. In this conversation with Erik Torenberg, they get into how you measure a model's ability to improve itself, why every good benchmark eventually has to be retired, and what happens when token spend begins to rival employee salaries. 00:00 Intro 02:20 Llama 4 on public vs private benchmarks 05:24 Nobody agreed how to test humans either 06:55 What movie ratings teach us about AI 08:55 The Enron problem in benchmarking 11:36 Why a good benchmark has to be retired 13:22 Evals that run for weeks, not seconds 16:20 Where the real workday starts at 4pm 18:08 A firm really is just its evals 20:35 Why Sonnet can cost more than Opus 22:42 One engineer, 6 billion tokens in a day 25:05 Who should set the rules for models 28:55 Public sector enforces, private verifies 33:32 Why sovereign AI is inefficient and happening anyway 35:00 The AI version of trust-but-verify 37:15 Where cyber evals have to go next YouTube: [youtube.com/watch?v=WO9c9q…](https://www.youtube.com/watch?v=WO9c9qxDxzU)[@RayanKrishnan](https://x.com/RayanKrishnan)[@ValsAI](https://x.com/ValsAI)[@bhorowitz](https://x.com/bhorowitz)[@JenniferHli](https://x.com/JenniferHli)[@eriktorenberg](https://x.com/eriktorenberg) [Your browser does not support the video tag.](https://video.twimg.com/amplify_video/2097688504574902273/vid/avc1/1920x1080/QBSg20UJEDvKUugD.mp4?tag=29) [🔗 View on Twitter](https://x.com/a16z/status/2097697391860232572/video/1)

来源报道 · 1 篇 · 以下链接均前往原始媒体

← 返回精选动态 原文

更多内容