🚨 New Course Announcement!
This Fall @Diyi_Yang@jyangballin and I are teaching a BRAND NEW Stanford course on how to build AI Agents from scratch!
Millions of users interact with AI Agents every day. Come join us and learn how to build them!
🧵 (1/5)
@paulomoreria lembro que tinha uma área da ouvidoria onde era possível abrir reclamação e eles são obrigados a responder e dar um motivo pelo atraso. salve todos os protocolos. na época que acionei, a entrega andou.
I am absolutely more productive using agents. I don't know the factor but it's large. However much of that productivity is spent tuning the agents and hardening the product. I'm guessing 30%-40%.
Some might consider that a waste; but I don't. The software I'm creating nowadays is vastly more robust than I'd ever been able to create manually.
I don't mean that the code is better. I mean the surrounding tests are vastly better. I have a higher degree of confidence than I ever had manually -- even when I used very disciplined TDD and Acceptance testing.
And then there's the ability to quickly reorganize the modules and the architecture while keeping those robust tests running. That is a tremendous boon.
@peterjordan foi bem mais ou menos. sem um desenvolvimento bom, algumas cenas bem sem sentido. mas é isso, não dava pra esperar tanto dada a última temporada. e pelo menos acabou, encerraram sem alongar demais a série. o trecho do bilionário do começo do ep foi engraçado!
We’re excited to announce that we’re making our SEGA logo 3% more blue.
We hope you enjoy this upgrade.
Please take a moment to familiarise yourself with the new look.
🔊Introducing Voxtral TTS: our new frontier open-weight model for natural, expressive, and ultra-fast text-to-speech
🎭Realistic, emotionally expressive speech.
🌍Supports 9 languages and accurately captures diverse dialects.
⚡Very low latency for time-to-first-audio.
🔄Easily adaptable to new voices
Qwen3.5 0.8B running real-time video captioning on a Mac Studio M2 Ultra.
<1s per frame.
269 frames from a 3m49s video.
Streaming descriptions as it plays.
Pause anywhere, it actually understands the scene.
~1GB model.
Local AI is getting unreasonably capable.
Video credit: @stevibe
Software horror: litellm PyPI supply chain attack.
Simple `pip install litellm` was enough to exfiltrate SSH keys, AWS/GCP/Azure creds, Kubernetes configs, git credentials, env vars (all your API keys), shell history, crypto wallets, SSL private keys, CI/CD secrets, database passwords.
LiteLLM itself has 97 million downloads per month which is already terrible, but much worse, the contagion spreads to any project that depends on litellm. For example, if you did `pip install dspy` (which depended on litellm>=1.64.0), you'd also be pwnd. Same for any other large project that depended on litellm.
Afaict the poisoned version was up for only less than ~1 hour. The attack had a bug which led to its discovery - Callum McMahon was using an MCP plugin inside Cursor that pulled in litellm as a transitive dependency. When litellm 1.82.8 installed, their machine ran out of RAM and crashed. So if the attacker didn't vibe code this attack it could have been undetected for many days or weeks.
Supply chain attacks like this are basically the scariest thing imaginable in modern software. Every time you install any depedency you could be pulling in a poisoned package anywhere deep inside its entire depedency tree. This is especially risky with large projects that might have lots and lots of dependencies. The credentials that do get stolen in each attack can then be used to take over more accounts and compromise more packages.
Classical software engineering would have you believe that dependencies are good (we're building pyramids from bricks), but imo this has to be re-evaluated, and it's why I've been so growingly averse to them, preferring to use LLMs to "yoink" functionality when it's simple enough and possible.
Add this paragraph to the https://t.co/CGO09Sihd0 file to turn Claude Code into Claude Teacher. Every project is a lesson to become more technical.
"For every project, write a detailed FOR[yourname].md file that explains the whole project in plain language.
Explain the technical architecture, the structure of the codebase and how the various parts are connected, the technologies used, why we made these technical decisions, and lessons I can learn from it (this should include the bugs we ran into and how we fixed them, potential pitfalls and how to avoid them in the future, new technologies used, how good engineers think and work, best practices, etc).
It should be very engaging to read; don't make it sound like boring technical documentation/textbook. Where appropriate, use analogies and anecdotes to make it more understandable and memorable."
O cinema brasileiro mais uma vez no topo do mundo! Sensacional a vitória do talentosíssimo Wagner Moura como Melhor Ator em filme de Drama no @goldenglobes.
A merecidíssima estatueta premia a performance de excelência do querido artista baiano que tanto nos emociona em O Agente Secreto.
Como o próprio Wagner tem dito, o cinema brasileiro vem mobilizando a atenção e o respeito das pessoas em todas as regiões, e tem sido um símbolo importante da volta da valorização dos artistas em nosso país.
Viva a cultura brasileira! 🇧🇷🎬 #OAgenteSecreto
Estamos muito felizes, eu e Janja, com a vitória de O Agente Secreto na categoria de Melhor Filme em Língua não Inglesa no @goldenglobes.
Viva o cinema brasileiro, que segue sendo sinônimo de orgulho nos principais palcos do mundo.
O troféu coroa o trabalho potente do querido diretor @kmendoncafilho e o seu extraordinário elenco.
Viva Wagner Moura, a incrível Tânia Maria, Alice Carvalho, Maria Fernanda Cândido, Hermila Guedes, Gabriel Leone, Carlos Francisco e toda a equipe que escreve mais um lindo capítulo da história do cinema brasileiro com essa premiação.
O Agente Secreto é um filme essencial para não deixar cair no esquecimento a violência da ditadura e a capacidade de resistência do povo brasileiro. 🇧🇷🎬 #OAgenteSecreto
Eu sei que você não perguntou, mas deixa eu te dar uma dica que eu gostaria de ter recebido quando era mais jovem: se o teu orientador não te coloca em projetos, não te inclui em grupos de pesquisa, não te repassa oportunidades de qualificação e não te convida nem para tomar um café, talvez seja o caso de arrumar outro orientador.