Esto es una auténtica joya.
Hace cinco semanas, Andrej Karpathy se unió a Anthropic.
Dos ingenieros senior de Anthropic llevaron el enfoque de Karpathy un paso más allá con el concepto de Graph Engineering.
Los sistemas agénticos mejoran de verdad cuando conectas los agentes en forma de grafo.
Lo integré en mi configuración y la primera respuesta ya fue completamente distinta.
No fue una mejora pequeña. Fue un cambio total.
Claude dejó de dar respuestas genéricas y empezó a trabajar exactamente como yo quería.
Guárdalo antes de que se pierda en tu feed.
Léelo ahora y luego échale un vistazo al artículo de abajo👇
September can't come soon enough 🔥
Join us for excellent content, a venue with character, and a room full of people who vibe.
Growth Phestival returns to Berlin on 15 September. Get one of the last remaining Early Bird tickets now: https://t.co/wVAbeC9T0p
@Gurmeta@Nanosecso Callate pulsaciones!!! No sabéis nada de deporte, y lo mostráis fuera y dentro del estadio, si supieran jugar tal vez, pero ni eso, 0 tiros a puerta, menos mal que está la ayuda del árbitros, si no ni oleis el césped en semifinales!!
@bcherny do you have any recommended setup for working with a meta-repo that contains several subrepos, especially when using worktrees?
In my case, I have a several meta-repo that includes multiple subrepos, and have CLAUDE.md that explain how works and integrate
A single 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 file just hit #1 on GitHub trending 🤯
It fixes LLMs' worst coding habits using 4 principles from Karpathy:
Karpathy called LLMs out for making wrong assumptions silently. They overcomplicate everything. They edit code they were never asked to change. No pushback. No clarifying questions. They just run.
So those observations were encoded into 4 behavioral constraints:
→ Think before coding. If something’s ambiguous, ask. Don’t pick one interpretation and run. Surface tradeoffs, stop when confused.
→ Simplicity first. Write the minimum code that solves the problem. No speculative abstractions, no flexibility nobody asked for.
→ Surgical changes. Only touch what the task requires. Don’t improve neighboring code, don’t refactor what isn’t broken.
→ Goal-driven execution. Turn vague instructions into verifiable targets before writing a line. “Add validation” becomes “write tests for invalid inputs, then make them pass.”
It works immediately.
Drop the file in your project root and Claude Code follows it from the first task.
One file. Zero dependencies. No setup.
And best part, 100% open source.
This isn’t a chatbot.
MiroFish Offline spins up a simulated world of agents that interact and evolve to explore outcomes.
Run it locally. Watch the system unfold.
• Swarm intelligence
• Parallel reasoning
• Offline execution
99% of people will never master claude prompt engineering.
Not because it's hard.
Because nobody showed them these 5 prompts.
Use them 10 times and you'll prompt better than people who've been at it for years👇
(Save this. The 99% won't.)
@GLS_Spain@GLS_clientes vuestro servicio es pésimo! 12h para entregas, a las 20:05, se marca como ausente... estando todo el día en casa esperando mi móvil, llevo 5 días sin él, como entenderéis me he quedado en casa para recibirlo, otro día más a esperar un repartidor 12h