unless the file I forgot to commit is the tests, which hopefully I'll catch by the time of the PR

I like it especially in concert with git commit --amend, which lets me tack my newest changes onto the previous commit. (Though an interactive rebase with fixup is even better)

The puzzles are all excellent, the writing is remarkable, both for game and fiction.

I probably picked the idea up here, but don't know from whom so I thought I ought to continue sharing it

So some places are optimizing their fries for delivery.

I've also noticed some restaurants are better at adapting the packaging, like punching out ventilation so fried products don't steam themselves in transit. Lawrence Seafood (which rules) did that for a side of tempura we got this weekend.

But I agree in large part. I wouldn't order fried chicken delivered via door dash in any event. People doing that are optimizing for something other than quality.

LLMs only have so much context available, so larger projects are harder to get good results in.

Some tools (eg a fast compiler) are very useful to agents to get good feedback. If you don't have a compiler, you'll get hallucinations corrected more slowly.

Some people have schedules that facilitate long uninterrupted periods, so they see an agent work for twenty minutes on a task and think "well I could've done that in 10-30 minutes, so where's the gain?". And those people haven't understood that they could be running many agents in parallel (I don't blame people for not realizing this, no one I talk to is doing this at work).

People also don't realize they could have the agent working while they're asleep/eating lunch/in a meeting. This is why, in my experience, managers find agents more transformative than ICs do. We're in more meetings, with fewer uninterrupted periods.

People have an expectation that the agent will always one-shot the implementation, and don't appreciate it when the agent gets them 80% of the way there. Or that, it's basically free to try again if the agent went completely off the rails.

A lot of people don't understand that agents are a step beyond just an LLM, so their attempts last year have colored their expectations.

Some people are less willing to attempt to work with the agent to make it better at producing good output. They don't know how to do it. Your agent got logging wrong? Okay, tell it to read an example of good logging and to write a rule that will get it correct.