2020: "Não vou tomar essa vacina que ninguém conhece, não confio nessa pesquisa."
2026: "Me vê 5 canetinhas daquele remédinho para emagrecer que achei num perfil do Instagram. Pode ser genérico, tanto faz."
Você está em uma aula online e quer copiar o texto de um slide do professor, ou quer extrair o texto de uma imagem... essa ferramenta é pra você! Ela já faz o OCR na hora. Funciona no Linux/Gnome.
Projetinho show de bola no vibe coding.
https://t.co/9X93KAibGK
The acceleration is accelerating and I now wonder if I was even too optimistic hoping that I still have a couple of years of software development ahead of me.
New Engineering blog: We tasked Opus 4.6 using agent teams to build a C compiler. Then we (mostly) walked away. Two weeks later, it worked on the Linux kernel.
Here's what it taught us about the future of autonomous software development.
Read more: https://t.co/htX0wl4wIf
claude code is fucking insane
i know literally NOTHING about coding. ZERO. and i just built a fully functioning web app in minutes
http://localhost:3000/
check it out
Anthropic just released ALL the Claude Code secrets
Their Prompting best practices just went live in their docs and I spent hours reading it and testing out all the tips
Here are the 10 that make Claude Code so much better: 🧵
Big moment for Postgres!
AI coding tools have been surprisingly bad at writing Postgres code.
Not because the models are dumb, but because of how they learned SQL in the first place.
LLMs are trained on the internet, which is full of outdated Stack Overflow answers and quick-fix tutorials.
So when you ask an AI to generate a schema, it gives you something that technically runs but misses decades of Postgres evolution, like:
- No GENERATED ALWAYS AS IDENTITY (added in PG10)
- No expression or partial indexes
- No NULLS NOT DISTINCT (PG15)
- Missing CHECK constraints and proper foreign keys
- Generic naming that tells you nothing
But this is actually a solvable problem.
You can teach AI tools to write better Postgres by giving them access to the right documentation at inference time.
This exact solution is actually implemented in the newly released pg-aiguide by @TigerDatabase, which is an open-source MCP server that provides coding tools access to 35 years of Postgres expertise.
In a gist, the MCP server enables:
- Semantic search over the official PostgreSQL manual (version-aware, so it knows PG14 vs PG17 differences)
- Curated skills with opinionated best practices for schema design, indexing, and constraints.
I ran an experiment with Claude Code to see how well this works, and worked with the team to put this together.
Prompt: "Generate a schema for an e-commerce site twice, one with the MCP server disabled, one with it enabled. Finally, run an assessment to compare the generated schemas."
The run with the MCP server led to:
- 420% more indexes (including partial and expression indexes)
- 235% more constraints
- 60% more tables (proper normalization)
- 11 automation functions and triggers
- Modern PG17 patterns throughout
The MCP-assisted schema had proper data integrity, performance optimizations baked in, and followed naming conventions that actually make sense in production.
pg-aiguide works with Claude Code, Cursor, VS Code, and any MCP-compatible tool.
It's free and fully open source.
I have shared the repo in the replies!
That's why vibe coding is way better from a phone. Not a computer.
- Take out your phone
- Send a prompt to Claude Code, Codex...
- Lock the screen
- Let it work
Building anywhere on mobile is way more efficient than waiting while staring at your laptop.
And you can set this up easily.
I'm using Replit on my phone and you can use both Claude Code and Codex (in addition to Replit Agent) anywhere.
1. Install the Replit mobile app (Android/iOS)
2. Create a new project
3. Launch the terminal
4. For Claude Code:
npm install -g (at)anthropic/claude-code-cli
For Codex:
npm install -g (at)openai/codex
Boom, you're done.