I've been using @mattpocockuk skills for the past couple of weeks, and my productivity has probably 3x'd.
My usual work session starts with the /grill-me skill. Begin with a broad, messy task, and the agent keeps asking questions until the gaps are clear. The useful part is that while you're answering, you're also forced to understand the task better and dig into the details you skipped. One time it grilled me for 80+ questions and halfway through I was basically asking are we there yet every few minutes.
Then I run /to-issues skill and kick the issues off in goal mode. One detail I think is very important is to explicitly ask it to spawn subagents for each task, test the work when it's finished, and redo it if it's not actually done. Runs usually go for multiple hours, so once one is kicked off, I can start working on another session, or just go back to doomscrolling.
I used Linux for years. For the past few months, I’ve been using Codex every single day.
Got tired of waiting for the Codex app on Linux, so I just bought a Mac for it.
First task: let Codex take over Chrome and clean up my X follows and lists. Felt great.
How might we craft an artificial society that reflects human behavior? My paper, which introduced “generative agents,” will be presented at #UIST2023 and now has an open-source repo! w/ @joseph_c_obrien@carriejcai@merrierm@percyliang@msbernst
https://t.co/yESmpevNlv 🧵