Switched to running a mix of claude and codex for the first time for day-to-day dev.
Opus 4.7's tendency to use acronyms drives me crazy, especially when I have no idea what it's referring to, even though I'm its collaborator.
TIL, "ennui": not just "nothing to do" but "nothing seems worth doing"
Why you need stateful agents. You can be ambiguous, concise, and still be successful because the agent has the surrounding context.
I really have enjoyed writing about building software in the past but lately I've been struggling to find a foothold. The prompts to an agent are now most of the software. There is trial and error...
I've been working on a chat app recently for collaboration with people and agents. I was heavily relying on "channels" for specific projects. However, a pattern that was emerging often was more...
There's a huge amount of cold outreach that appears (to my eye) to be LLM-generated. What's more interesting that these inbound messages seem completely decoupled from the human(?) who gets involved...
I spent yesterday working on a personal project to build some software with my personal agent, struggling mightily when I didn't expect to. Opus 4.7 was recently released. And in the back of my mind...
Coming from a software engineering background, but mostly spending time teaching non-technical domain experts how to code has been an interesting challenge because my first impulse or inclination is...
The Cowork and Claude Code UIs are friendly on ramps for agent tools, particularly for nontechnical roles, but I do wonder whether hiding the more technical aspects of the system makes users less...