AI has a deep understanding of how this code works

Re:AI has a deep understanding of how this code works by pluc on Tuesday November 25, 2025 @09:07AM (#46045888)

He's doing it elsewhere too:

https://github.com/rerun-io/rerun/pull/11900#issuecomment-35...

https://github.com/ocaml/dune/issues/12731

https://github.com/tshort/StaticCompiler.jl/pull/180

Seems he's just on a rampage of "fixing" issues for trendy packages to get some attention.

[ Parent | on HN ]

Re:AI has a deep understanding of how this code works by footy on Tuesday November 25, 2025 @09:13AM (#46045934)

> I like a tough challenge and I was hoping to attract your attention.

thanks for the comedy material.

[ Parent | on HN ]

Re:AI has a deep understanding of how this code works by wagerlabs on Thursday November 27, 2025 @04:41AM (#46067522)

I had $1000 in Claude credits to spend for the greater good.

[ Parent | on HN ]

Re:AI has a deep understanding of how this code works by pluc on Thursday November 27, 2025 @08:47AM (#46069190)

You didn't

[ Parent | on HN ]

Re:AI has a deep understanding of how this code works by snickerbockers on Thursday November 27, 2025 @02:33PM (#46072514)

Personally I would have those credits to generate hentai but to each his own i suppose.

In the post where you had it respond to accusations of plagiarism and it responded by posting snippets of code which were obviously plagiarized and confidently asserted that they were not, what was your prompt? I ask because I felt its response was oddly tone-deaf even by LLM standards. I'm guessing that instead of giving it a neutral prompt such as "respond to this comment" you gave it something more specific such as "defend yourself against these accusations"?

I'm used to seeing them contradict themselves and say things that are obviously not true but usually when confronted they will give in and admit their mistake rather than dig a deeper hole.

[ Parent | on HN ]