VMG

where is the source for this claim?

What matters is the token count and logprob. It hurts but it's true

It feels like the day after I got comfortable with jj everybody become obsessed with git worktrees

Hey at least you know it's not Claude

...... or do you???

Right but there are probably 100-1000 important domains and a long tail of less important ones

In the case, the purported conspiracy was that the powerful forensic pathologist was protected by a shadowy elite

Funny because it reads almost exactly as a Ferdinand von Schirach story

No, I don't want to see the prompt. Yes it has some llm tics, but it's clear that he went back and forth before arriving at this. Why would I be interested in the transcript?

Slop is a new language and you will learn it read it

LLMs are sometimes stupid and get confused when you change the files without them knowing. So asking them to do even simple things keeps the context in sync.

Plus you get a bonus random line "methods are all on the top" in the commit message that makes no sense to anybody.

> If you haven't tried jj yet, take it for a spin and see how you like it.

And if your muscle memory doesn't allow an immediate transition, give yourself 2 weeks. That's how long it took for me at least.

Invest in custom tooling and helper scripts.

fair, but we are approaching the point where it gets difficult to tell where the human still is involved

for all intents an purposes, the paper as well as the lean repo could be full LLM output with zero human involvement

`solution.lean` is a 12mb file

I looks like we are breezing past the point where unassisted humans can understand any of this