The abuse (in my opinion) of the auto-translate feature is super annoying. Thanks goodness for โblockโ.
Any conversation
โโโโโโโโโโโโโโโโโโโโโ
โโโโโโโโโโโโโโโโโโโโโ
โโโโโโโโโโโโโโโโโโโโโ
โโโโโโโโโโโโโโโโโโโโโ
โโโโโโโโโโโโโโโโโโโโโ
โโโโโโโโโโโโโโโโโโโโโ
โโโโโโโโโโโโโโโโโโโโโ
โโโโโโโโโโโโโโโโโโโโโ
โโโโโโโโโโโโโโโโโโโโโ
โโโโโโโโโโโโโโโโโโโโโ
โโโโโโโโโโโโโโโโโโโโโ
Last year I wasn't feeling too good.
I turned forty, waited for surgery, and was hurt by my own colleagues. So I dealt with things. Maybe not so well, but to the best of my ability.
One of the consequences was that I got a bit heavy. My body changed, and I didn't feel like myself. It was a problem for future me. So now I am here with this little belly of mine. We're not enemies, but I decided it's time to part ways.
So I count calories. Maybe not so well, but to the best of my ability.
Routines in Claude Desktop create Claude Code sessions, so hourly routine litters in iPhone' Claude.app Code tab. Screw it, built my local version of AWS StepFunctions - Stepper - and run skills as state machines there.
I notice that language models are much better at programming than at writing. This is largely because, in programming, they have a closed feedback loop that allows them to find errors. Writing is much more complicated because the feedback is much more diffuse and delayed over time. In fact, it is often not well-defined.


