Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

LLMs corrupt your documents when you delegate

arxiv.org

Post reply on HN
Print view View original

231–235 of 235 posts

Re: LLMs corrupt your documents when you delegate

#231

Post by Kim_Bruning »

oblio wrote: post #228
Kim_Bruning wrote: post #218

Earlier quoted context omitted.

No wait, you think I'm being silly so that's why you're being a bit sarcastic back. But seriously, you can put a shebang on an english text file now (if you're sufficiently brave), or feed it through something that spits out code on the other end (so you can proof read the consequences before executing them). It's crazy, but this is 2026, and that actually ... just works. You can even do it locally, if you don't mind…

> But seriously, you can put a shebang on an english text file now (if you're sufficiently brave), or feed it through something that spits out code on the other end (so you can proof read the consequences before executing them). The funky thing is that it's not just English. I could vibe code in Romanian, it would probably be hilarious :-)) Probably not for whomever would have to take over the app, though.

Eh? You should go for it! Do everything at least once, right? Pick some simple pet project, and get it off your bucket list!

If it wasn't on your bucket list to begin with, who cares: Now you can add it and complete it in one fell swoop ;-)

Re: LLMs corrupt your documents when you delegate

#232

Post by embedding-shape »

deadbabe wrote: post #215
embedding-shape wrote: post #194

Earlier quoted context omitted.

> then jumping in last minute after everyone has struggled through figuring out how to use them still puts you on the same level very quickly Does it actually though? I've used agents for quite some time now, if someone who never used agents before want to put this to the test somehow, I'm open to try to measure this, reach out via email :)

What would you even propose as a test

Can be anything, refactor of old thing, build new thing, change existing thing, something like "Do X in Y hours/days, then we compare the results", and we'll see if there is any differences. Do it a couple of times, you might be able to figure out how to measure it as you discover the better methodologies.

Re: LLMs corrupt your documents when you delegate

#233

Post by wfurney »

simonw wrote: post #227
Kim_Bruning wrote: post #218

Earlier quoted context omitted.

No wait, you think I'm being silly so that's why you're being a bit sarcastic back. But seriously, you can put a shebang on an english text file now (if you're sufficiently brave), or feed it through something that spits out code on the other end (so you can proof read the consequences before executing them). It's crazy, but this is 2026, and that actually ... just works. You can even do it locally, if you don't mind…

> But seriously, you can put a shebang on an english text file now (if you're sufficiently brave) That inspired me to figure out how to do exactly that: https://til.simonwillison.net/llms/llm-shebang #!/usr/bin/env -S llm -f Generate an SVG of a pelican riding a bicycle Thanks for the inspiration!

A .llm file extension might be in order :)
Post reply on HN