@phosphenq

Article

The full harness I run, the exact steps and install blocks to build your own, and the receipt from a mid-tier model hitting frontier-level output....

@jota_snchez

Thread

Robert Sapolsky es un neurocientífico de Stanford que demostró que el estrés es el asesino silencioso que los médicos ignoran. Reveló 10 hábitos que haces todos los días y que te quitan años de vida. 1) Repasar conversaciones en tu cabeza ...

@Mnilax

Article

Everyone's telling you to stop prompting and build loops. Almost nobody shows you the setup the people who built Claude Code actually recommend: <b><i>/goal</i></b><i></i>, a separate verifier, worktree isolation, real stop conditions....

@jota_snchez

Thread

Un profesor recopiló 50 años de estudios sobre quién triunfa en la vida. Su conclusión incomoda: casi todo lo que crees sobre el éxito es consecuencia, no causa. 8 verdades incómodas sobre quién triunfa y por qué: 1. Te vendieron 3 recetas del éxito y las 3 tienen trampa ...

@0xhalaler

Thread

Are you still paying for your LLM's tokens? Or has it found its own money? <a target="_blank" href="https://twitter.com/0xhalaler/status/2073686060706717797" color="blue">x.com/0xhalaler/stat…</a>...

@0xCodez

Article

Most developers still prompt their coding agents by hand. They type, they wait, they read the diff, they type again. <b>9</b>out of 10 builders have never written a single loop that prompts the agent for them....

@0xMovez

Article

The leverage in investing moved. It’s no longer about watching charts faster - it’s about designing the loop that researches, decides, and trades for you. ...

@OpenAI

Thread

We’re expanding OpenAI Daybreak to help democratize patching vulnerable software at machine speed: - Codex Security plugin: find, validate, and fix vulnerabilities right inside Codex - The full version of GPT-5.5-Cyber model: a great model for trusted defenders - Cyber Partner Program: powering p...