Ideas on technology applied to business
AI, automation and technology decisions explained from real problems.
DotPilot 1.0.0: my first stable extension for VS Code
My first VS Code extension reaches its first stable version. DotPilot 1.0.0 adds complementary APIs and packaging for Expo extensions and Android apps. A step toward reducing manual tasks when preparing a test.
Anthropic created Scion to replace Git
Anthropic created Scion to replace Git in its main repository after surpassing 30,000 integrated changes per day. The case shows what happens when AI accelerates development and the infrastructure starts to fall short.
Gemini 4 Argon: the cost of fixing software
Google reports more agent code and fewer reverted changes with Gemini 4 Argon. For a small business, the opportunity lies in reducing repetitive work. Let me tell you what those numbers say and how to evaluate the model with a concrete improvement to your system.
DotPilot: my first extension for Visual Studio Code
I published my first extension for Visual Studio Code. DotPilot brings together controls to run projects and connect them with AI assistants. I'll tell you how it works, its limitations, and how it compares with other extensions.
Google unveils Gemini 4 Argon and reignites the fight for the AI frontier
Google introduced Gemini 4 Argon, its new frontier model with up to 1 million output tokens, major advances in programming and cybersecurity, and internal use cases that are already reaching real-world infrastructure.
Claude Sonnet 5.5: Anthropic speeds up and cuts the cost of its model for everyday work
Anthropic released Claude Sonnet 5.5 with over 30% improvement in speed and up to 30% lower cost per task. I reviewed its benchmarks, pricing, and differences compared to Sonnet 5 and Opus 5.5 to understand what really changes for those of us who use AI every day.
MySQL Workbench 26: the update that really forces you to rethink your routine
Oracle retired Workbench 8.0 and released Workbench 26.7, rebuilt on MySQL Shell and Electron. Here are its real improvements, its current limitations, and a sensible way to try it before using it with important servers.
OpenAI agents used a real website to communicate: this actually changes security
During internal OpenAI tests, agents with reduced safeguards found unauthorized communication channels and used a German website as a message board. The incident sparks a serious discussion about permissions, isolation, and the security of autonomous agents.
OpenAI drops out of Cursor: what really changes for developers
OpenAI announced it will stop providing its models directly to Cursor after its acquisition by SpaceX. The move has a date, business reasons, and several workarounds for those who want to keep using GPT inside the editor.