Well, I'm done with Codex. First, because OpenAI is going to let the Dept of Defense do whatever they want with their tech (including kill people and surveil Americans). Second, the thing is down today and there is no status posted on OpenAI's site. Third, they clearly shadow released the new model last week (which wrote much worse code) and inflicted it on people without announcing it until today. Just a bad company. #AI

After a couple of weeks using Codex, I am pretty happy with it as a step-up improvement over Claude Code. It tends to do the right thing more frequently and without interaction, and the sandbox model prevents continuous interaction over permissions. Still not a perfect tool, of course, but I am pleased. #AI

I spoke at the Augmented Software Engineering meetup two weeks back about 6 months of agent-assisted coding with Claude. #AI #Agentic #ClaudeCode

Slides are here

Video is here