- merge conflicts
- Try speculative things to learn from working examples
- @withoutclass on Mastodon:
I found it confusing that I was feeling more burnt out from using them than less, but I also realized I was context switching way more while waiting for the robot on top of having to articulate thoughts more to the robot as well.
- Building understanding of large codebases via speculative prototypes and arguing with the agent
- Carson Gross:
it is interesting to see where AI did well, namely in investigation and test creation, and to contrast that with where it didn’t do so well: coming up with a clean solution. difference is Taste.