CIRCLE WITH A DOT

@tiotasram I remember wondering the same about world wars and genocides​

@glyph it's difficult to understand why anyone with Cory's reputation would decide to die on such ridiculous hill ​

@cuboci @AndrewRadev I wish I had the patience left to be so charitable, but every project I've seen which has used LLMs in this fashion has eventually accepted PRs with glaring security holes.

Even if they're doing their best under difficult circumstances, it's still an unacceptable risk in my perspective, and I'm going to have to start seriously considering alternatives even if I don't switch immediately.

So, perhaps that slow death has already begun ​

@cuboci @AndrewRadev somehow I do not find it comforting that the last line against slop in software I use is review by another slop-machine

@root @cuboci @AndrewRadev sorry, didn't realize we were doing a "wrong answers only" thread

@cuboci @AndrewRadev I'm not gonna say I won't learn something new if I have sufficient reason to do so, but it would be incredibly frustrating to have to do so for such a ridiculous reason.

By all accounts Bram Moolenaar seemed like a good person, and it's terrible to see his project being (mis)managed in this way.

@cuboci @AndrewRadev most definitely not. I honestly have no idea.

neovim also has commits from claude, so that's not it either.

Maybe somebody will fork from a pre-slop version?

@AndrewRadev ugh.

I've been using vim for like.. 15 years? I thought it was unlikely to get caught up in the fad-chasing that seems to affect so many other editors.

I do not want to have to switch, but now I feel like I might have to

@joeyh I'm glad to see that someone else has considered this angle. It's always bugged me a little when I see the "they aren't deterministic" argument, but I've kept it to myself because nobody likes a pedant and of course @cwebber already understands as much.

I just worry that if this critique were to become more popular then the LLM makers would just implement the ability to specify a seed, then sit back and play the game where they say

we heard your criticism and have addressed it

Most people have no reason to have developed an advanced reasoning capacity about randomness, and I dread having to explain to them how something can be both deterministic and stochastic in nature ​