Mentioned elsewhere but classic ml seems the right tool for this problem

I cannot feel anything but schadenfreude regarding anthropic having its IP stolen from it. Bravo Chinese labs, bravo

There is a purely strategic reason for keeping some hand code skills exercised. If you outsource the coding away completely you become dependent on entities that can pull the plug on you. Not arguing it's the right choice to rein in the agentic coding just that there is some rationale for doing so

I've noticed this bug before too. Seems like an old one

I blame the hidden context on the tools/subagents. One recent example.. codex can just look in the code for Db schema but continually tries to request permission for a live db query

Fixing our problems will still require human effort and human cooperation. No text output however intelligent or true or eloquent will change that.

Politics and problems don't stem from the story. The story is an after the fact rationalization

Very poetic metaphor!

Also a codex user but for me brevity is not it's strong suit. I basically have to give it bigger tasks than I am used to to warrant the time it takes to complete. I feel whatever context the tooling adds can also be problematic

> bigger tasks than I am used to

Do they still get split into commits in sensible ways, for you?

I use beads to create tasks and typically it can hammer out a beads task and then commit under the task id

…sorry, "beads"?

Gastown lingo: https://github.com/gastownhall/gastown

an actual tool https://github.com/gastownhall/beads

Some of these work tools can slow things down and waste plentiful tokens