全部 AI 动态

https://x.com/i/article/2112152891670896640

added Fish Audio’s Drama-3 to speech-to-speech 🎭 cloned my voice. now I can ask it to whisper, laugh, sigh or get worried, just by talking. cheers to @andimarafioti for the demo + sampling tips! PR + setup: https://github.com/huggingface/speech-to-speech/pull/725

Another fantastic use case for personal agents: study prep I'm preparing for a technical certification right now, and I've trained my @Muse agent on all of the prep exams / materials. Then, I have it sending me random pop questions throughout the day, tracking my progress. After weeks of not being able to find hours to sit down and study, this method has worked very well for me: about a question or two each hour of the day, outside of the meetings that I am in (it knows my calendar). Highly recommend!

Give your agent a way to verify its work. This can dramatically improve the quality of output. With this process in place, Claude Code was able to write 90%+ of its code itself. When generating software at a faster rate than you can review it, the bottleneck shifts to proving that it works. @bcherny and team invested enough in verification, we've been able to move fast while maintaining stability. Code reviews aren't going away, but you need to think of it differently. One human reading through line-by-line is no longer going to work as a gate, it needs to evolve into a multi-layered verification system, built with fast deterministic feedback loops for your agents. This is where e2e tests, feature maps (as @poteto has been advocating), property tests and multi-agent adversarial reviews come in. These all provide opportunities to catch errors early and fix them before things get out of hand. You don't have enough eyeballs for the amount of code being written so your focus needs to be on product intent, risk assessment and evaluating evidence rather than reviewing code. Delegate the code checking work to your automated tests, scale your approvals based on risk, and turn your test failures into living evaluations. This approach helps maintain speed without losing reliability. Let the agents do what they do best and let you focus on what makes you irreplaceable: judgement, direction, and ownership. We tried to capture how we handle code review and verification in this writeup. Hopefully it's helpful.

Stanford、CMU 和 MIT 三所顶级大学的 5 门 AI 课程之外，再分享两门更偏理论和基础的课程。 CS336: Language Modeling from Scratch Stanford AI 课程链的顶点实现课，由 Percy Liang 与 Tatsu Hashimoto 联合执教，从零亲手构建一个完整的语言模型。 CS221: Artificial Intelligence: Principles and Techniques Stanford AI 的本科主干入门课，由 Percy Liang 执教，用统一的数学框架（学习、搜索、MDP、博弈、贝叶斯网络、逻辑）把整个经典 AI 领域走一遍。 这两门课程都来自 Stanford 大学，讲师都有 @percyliang (@stanfordnlp 教授，@togethercompute 联合创始人）。 CS336 课程地址 https://cs336.stanford.edu/ https://www.youtube.com/playlist?list=PLoROMvodv4rMqXOcazWaTUHhq-yembLCV CS221 课程地址 https://stanford-cs221.github.io/autumn2025/ https://www.youtube.com/playlist?list=PLoROMvodv4rMeDqwS1yFl3j3sR_-MQNEN

If we only use AI to make the things that we already make, just faster, then we're definitely missing out on the most interesting part. From my talk at @lennysan’s Summit, here are four ideas for raising the ceiling, not just the floor: - Have a point of view [5:38] - Encode your standards into the machine [9:07] - Don't confuse done with good [12:21] - Unleash creativity and artistry [16:19] Full talk here: https://youtu.be/GLvFTMtw4Jk?si=-5TsYAjoFtgJBUS4