Nowadays I barely write code without an LLM, and my OSS productivity has gone through the roof. Look at what I've shipped on #Twig lately (more to come). Steve Yegge's 8 levels of AI-assisted development described my last 2 years exactly.

🏃‍♂️‍Estamos llegando a ese momento del año en el que las empresas vienen a contratar con prisas y desesperación. Han agotado sus bazas: han intentado buscar por su cuenta candidatos pero, por lo que sea, no han podido contratar en los primeros 6 meses ese/esos rol/es que necesitan. En la mayoría de los casos, nos llegan empresas a que no tienen muy claro el cambio que ha sufrido el mercado y tenemos que aterrizarles un poco. Ahí van algunas zonas comunes que pueden ser útiles para candidatos y empresas. 1. La presencialidad se paga. Las ofertas híbridas conllevan un rango salarial un 20% superior a una oferta remota. 2. La estacionalidad es real. Todo el mundo quiere cambiarse en dos momentos concretos del mercado: marzo-abri-mayo y septiembre-octubre. 3. El pool de talento dispuesto a entrar en procesos de selección y/o cambiarse en estos meses de julio y agosto es menor. 4. El mercado está un poco loco: todo el mundo quiere AI engineers. La realidad es que no hay suficientes perfiles formados y con experiencia como se necesitan. Si no pagas por encima de mercado, lo tienes muy muy complicado. 5. Los unicornios no existen. Si estás buscando un all-in-one full-stack terraneitor siento quitarte la ilusión. No lo vas a encontrar. Busca un perfil fuerte en una especialidad y que se apalanque en la IA para poder tocar el resto del SWLC. 6. Los candidatos se quieren mover. Llevamos récord de aplicaciones anual con casi 12K aplicaciones a ofertas en estos primeros 6 meses del año. Mayo ha sido el mes con más aplicaciones de la historia de Manfred. Y con esto, cierro con dos cosas: 1) No hay nadie con un volumen de aplicaciones de candidatos de calidad como Manfred ahora mismo. 2) No hay nadie que te hable de esto ni que te enseñe estos datos. Tú sacas las conclusiones ;) Si estás en esta situación o tu empresa lo está y no está contratando al equipo que necesitáis, podemos echar un cable. Pero el momento es ahora. Si no, te vas a septiembre y te comes el año entero :S Entiendo que a veces somos la última opción, porque te cobramos por nuestro trabajo. Pero siempre me queda el pensamiento de si no te sale más rentable que te ayudemos a contratar y en febrero-marzo tengas a alguien en el equipo a tener que esperar a julio-agosto para hacerle el onboarding a alguien en verano y con 6 meses menos de tiempo y desarrollo. 🤷‍♂️ getmanfred.com y tal

🚀 Introducing Gemini-SQL2, our breakthrough text-to-SQL capability powered by Gemini 3.1 Pro! We've achieved state-of-the-art results on the highly competitive BIRD benchmark, translating natural language into execution-ready SQL queries. 🧵👇

We’ve added a CLI for Claude Platform to make every API endpoint runnable from your terminal. Call the Messages API, stand up Claude Managed Agents, pipe results straight into your shell. The ant CLI is well understood by coding agents (Claude Code) using the claude-api skill.

How powerful is Gemini 3.5 Flash? In a recent research preview, we pushed it to the extreme, powering 93 subagents across 15,314 model calls that wrote a custom kernel, filesystem, and drivers from scratch. 12 hours later, it booted Doom. 🖥️ This is just a glimpse of the model's reasoning depth and code generation capabilities. Full breakdown below 👇

Opus 4.8 is live in Claude Code today. A few things worth knowing: 🧵

🔒An update on Composer & Packagist supply chain security: what's in place, what ships this week with Composer 2.10 (dependency policies, immutable versions), and what comes next. If you maintain PHP packages, enable MFA now! #php #phpc #composerphp

You might believe you should spend less time thinking about code because of AI. I strongly disagree! We’re watching this play out live where tons of AI generated code becomes a liability. At the end of the day, an engineer needs to be responsible / on call for code that gets shipped to production. If you don’t understand the system you’re trying to debug, you’re probably going to have a bad time. Yes, AI can help with all of this, if you set up the proper systems. You can have agents triage prod logs, look at errors, etc. You can speed up parts of the investigation, but an engineer needs to make the call. There might be serious customer or financial implications from that change. I expect the trend continue for trimming dependencies, vendoring code so you can modify it directly, preferring simpler systems with fewer abstractions, and spending waaaay more time thinking about system design and code maintenance. I’ve said this before, but it’s a great time to get familiar with CS fundamentals and some of the history behind what great software looks like. Many parts will be different in the coming years as AI progresses, but also a lot more than people realize will stay the same.

Skills should be: - Concise - Responsible for one thing, not multi-step - Composable - Progressively disclosed - Harness-agnostic What else? Or - what did I get wrong?

Claude Mythos Audited Symfony and Found 19 Vulnerabilities 👉 symfony.com/blog/claude-myth… #PHP

During the last few weeks, the #Symfony core team has been hard at work fixing a long list of vulnerabilities for both #Symfony and #Twig. Today, we're publishing that work in the biggest security patch releases ever. Bare with us and wish us luck 🍀

Introducing Antigravity 2.0, a new standalone desktop application that delivers fully on that original glimpse of a truly agent-optimized experience. Rebuilt from the ground up with multi-agent teams, scheduled tasks, native voice and one-click integration with other Google products. Learn how to get started with Antigravity 2.0 👇

Quando você não tem pendrive ou rede e precisa transferir os arquivos de qualquer modo 🤯🤯🤯

People freaking out over my AI spend. What nobody sees: Part of what excites me so much about working on OpenClaw is that I'm trying to answer the question: How would we build software in the future if tokens don't matter? We constant run ~100 codex in the cloud, reviewing every PR, every issue. If a fix on main lands, @clawsweeper will eventually find that 6 month old issue and close it with an exact reference. We run codex on every commit to review for security issues (as it's far too easy to miss). We run codex to de-duplicate issues and find clusters and send reports for the most pressing issues. We have agents that can recreate complex setups, spin up ephemeral crabbox.sh machines, log into e.g. Telegram, make a video and post before/after fix on the PR. There's codex that watch new issues and - if it fits our documented vision well, automatically create a PR of it. (that then another codex reviews) We have codex running that scans comments for spam and blocks people. We have codex instances running that verify performance benchmarks and report regressions into Discord. We have agents that listen on our meetings and proactively start work, e.g. create PRs when we discuss new features while we discuss them. We build clawpatch.ai to split all our projects into functional units to review and find bugs and regresssions. We do the same split for security with Vercel's deepsec and Codex Security to find regressions and vulnerabilities. All that automation allows us to run this project extremely lean.

We released Claude Opus 4.6 just two months ago. Today we're sharing some info on our new model, Claude Mythos Preview.

🚨 You need to see this. @addyosmani from Google just dropped his new Agent Skills and it's incredible. It brings 19 engineering skills 7 commands to AI coding agents, all inspired by Google best practices 🤯 AI coding agents are powerful, but left alone, they take shortcuts. They skip specs, tests, and security reviews, optimizing for "done" over "correct." Addy built this to fix that. Each skill encodes the workflows and quality gates that senior engineers actually use: spec before code, test before merge, measure before optimize. The full lifecycle is covered: → Define - refine ideas, write specs before a single line of code → Plan - decompose into small, verifiable tasks → Build - incremental implementation, context engineering, clean API design → Verify - TDD, browser testing with DevTools, systematic debugging → Review - code quality, security hardening, performance optimization → Ship - git workflow, CI/CD, ADRs, pre-launch checklists Features 7 slash commands: (/spec, /plan, /build, /test, /review, /code-simplify, /ship) that map to this lifecycle. It works with: ✦ Claude Code ✦ Cursor ✦ Antigravity ✦ ... and any agent accepting Markdown. Baking in Google-tier engineering culture (Shift Left, Chesterton's Fence, Hyrum's Law) directly into your agent's step-by-step workflow! `npx skills add addyosmani/agent-skills` Free and open-source. Repo link in 🧵↓

@taylorotwell casually shipping a broken app online. The app triggers an alert, which triggers opencode which writes a fix, pushes a PR, then OpenClaw calls Taylor BY PHONE on stage, who responds « merge it », and the fix is merged and deployed. All in 2 minutes, live on stage 😂

I asked ChatGPT and Grok: I want to wash my car, and the car wash is 50m away. Should I walk or drive? Grok: Drive because the car literally needs to be at the car wash to get washed. ChatGPT: Walk! ChatGPT is so dumb.

We've added a new command to Claude Code called /insights When you run it, Claude Code will read your message history from the past month. It'll summarize your projects, how you use Claude Code, and give suggestions on how to improve your workflow.

Most people are terrified AI will take their jobs because they confuse their tasks with their purpose. Jensen Huang explains it perfectly: If you watched a CEO all day, you would think their job is "typist" because they spend most of their time typing emails. If AI automates typing, the CEO doesn't lose their job. They just have more time to lead. The same applies to everyone. When AI automates the tasks, it enhances the purpose. Stop measuring your value by your to-do list. Your value is the purpose behind it.