Agentic coding could help a lot for the latter, not necessarily the former.

Much of the cognitive work in writing emerges in the labor of writing prose and challenging assumptions against the model you build in your head as you go. I've found this process is inverted when working with an LLM: it in effect emits a provisional structure first, and I discover what I actually think by finding where its output is vague, overconfident, incomplete or outright false.

Accepting surface-level coherence as finished thought is the failure mode to avoid.

[0] https://files.catbox.moe/eqg0b2.png

Once in frustration I called a certain frontier model "Sam Altman's Tin Bird" to another agent with memory, and ever since then that other agent refers to ChatGPT as "the tin bird". Definitely a RAG artifact more than an attractor in that case, but I found it amusing.

What I absolutely can’t stand is the routing. It once tried to send me through residential Oakland on some Manhattan-grade staircase labyrinth instead of just taking normal streets.

What's weird is that I love EVE for that sort of nullsec drama and sociopathic players eating each other in crazed gambits, but a couple of matches in Overwatch competitive a decade ago put me off the idea of matchmaking lobbies altogether.

I've seen many native English speakers routinely bang out "airforce", so it's not just an ESL thing.

Another thing is that these games are often made to run on a wide variety of graphics and sound hardware, and effectively have drivers compiled into them.

[0] https://github.com/keirf/greaseweazle

I do have one teeny, tiny, personal pedantic grumble that is sure to bring other the branches out of the woodwork to point out how much I love chairs.

Air Force. Two words. Thanks.