I can now probably say this:
Two months ago, inside Anthropic someone suggested building a token leaderboard.
A heated internal debate followed and the decision was made to *never* ever do it… because several people inside Anthropic simply thought ahead of the consequences
This works surprisingly well:
• Ask Claude Code to fix a bug
• Let it work and figure it out
When it finishes, use this prompt:
"Knowing everything you know now, delete your fix and implement a better|concise|elegant version."
Claude will use the first pass to explore and learn the problem. Sometimes, this will lead to suboptimal code.
The second pass will be better because Claude already knows the problem and can write a better solution.
This GitHub incident is insane. Merge queue commits have been reverting previously merged commits at random.
This not only breaks the mental contract teams have with Git in general, but is subtle enough to be really hard to unravel after the fact.
https://t.co/C8vbDGqdmC
¡Vuelve DeepSeek! Han lanzado de código abierto la V4.
Versiones: Flash y Pro. Contexto de 1 millón de tokens.
No es el mejor modelo pero es...
¡20 veces más barato que Opus 4.7 y GPT 5.5!
Para muchos casos de uso va a ser más que suficiente:
GStack is an open-source toolkit built by YC President & CEO @garrytan that turns Claude Code into an AI engineering team — with skills for office hours, design, code review, QA, and browser testing.
In this video, Garry walks through how GStack works, starting with Office Hours, a skill modeled after real YC partner sessions that pressure-tests your idea before you write a line of code. He demos it live, going from idea through adversarial review, design mockups, and automated QA in a single session.
Memory on Claude Managed Agents is now in public beta.
Your agents can now learn from every session, using an intelligence-optimized memory layer that balances performance with flexibility.
Computer use is now in Claude Code.
Claude can open your apps, click through your UI, and test what it built, right from the CLI.
Now in research preview on Pro and Max plans.
Hice un Dependency Injection Container para Kotlin, con la rica sazón que siempre quise que un container tenga. Aquí les dejo el artículo por si quieren darle un ojito: https://t.co/80AbEwxCku
New in Claude Code: auto mode.
Instead of approving every file write and bash command, or skipping permissions entirely, auto mode lets Claude make permission decisions on your behalf.
Safeguards check each action before it runs.
I've been having such an amazing time with Claude Code I wanted you to be able to have my *exact* skill setup:
Introducing gstack, which you can install just by pasting a short piece of text into your Claude code
¡Trucazo con GitHub! Añade un 0 a la URL de una Pull Request para que una IA te ayuda a revisar y entender los cambios que quieren fusionar. Sin coste. Te lo explico ↓
Si quieres entender Big O Notation de una vez por todas, esta guía es una joya.
Ejemplos interactivos, diagramas claros y explicaciones sencillas.
En la universidad hubiera pagado por tener algo así.
Si te dedicas a programar, lo tienes que leer:
→ https://t.co/O1PCKHUryU