I remember a conspiracy nut telling me "the truth", saying not to believe what the media told me, and do my own research. And then proceeded to point me to a few conspiracy influencers that were telling him what to think. It was very ironic.
> And for in-place edits, you can review "git diff" for surprises.
I don't let AI touch git anyway, and I always review the diff after it generated stuff. If it modifies my documentation, I always want to check if it messed with the text instead of just added formatting.
This. I know the LLM agents often have their own little diff viewers and edit approval workflows, but for a high volume of code, I cannot imagine actually reviewing everything without leaning on much more capable Git tooling.
I use Magit, and up until I started using LLM agents it was mostly a nice-to-have that I relied on casually. (I was definitely under-utilizing its power.) But for reviewing, selectively staging, and selectively rejecting the changes of an LLM agent? I feel like I'd die without it. Idk how others manage.
It reminds me of the footage of Doom running on a pregnancy test. And then it turned out it was another computer just displaying to the build in AMOLED display.
What was supposed to be a cool achievement is rendered pointless when one of the key elements is offloaded elsewhere.
They did add nuance to that quote a long time ago. It's a good stance, it's fine if someone knows something to be true. But other visitors of Wikipedia don't know that, so anything that's added without a source is questionable.
reply