←back to thread

Using Claude Code to modernize a 25-year-old kernel driver

(dmitrybrant.com)
925 points dmitrybrant | 1 comments | 07 Sep 25 23:53 UTC | HN request time: 0s | source
Show context
rmoriz ◴[08 Sep 25 02:32 UTC] No.45164188[source]▶
I was banned from an OpenSource project [1] recently because I suggested a bug fix. Their „code of conduct“ not only prevents PRs but also comments on issues with information that was retrieved by any AI tool or resource.

Thinking about asking Claude to reimplement it from scratch in Rust…

[1] https://codeberg.org/superseriousbusiness/gotosocial/src/bra...

replies(7): >>45164303 #>>45164375 #>>45164387 #>>45165103 #>>45167034 #>>45168743 #>>45169162 #
bgwalter ◴[08 Sep 25 11:34 UTC] No.45167034[source]▶
There is no "from scratch" for "AI". Claude will read the original, launder it, strip the license and pass it off as its own work.
replies(1): >>45167427 #
TuxSH ◴[08 Sep 25 12:24 UTC] No.45167427[source]▶
Indeed, LLMs cannot do truly novel thinking, and the laundering analogy is spot-on.

However they're able to do more than just regurgitating code, I can have them explain to me the underlying (mathematical or whatever) concept behind the code and write new code from scratch myself, with that knowledge.

Can/should this new code be considered as derivative work, if the underlying principles were already documented in literature?

replies(1): >>45167691 #
1. wizzwizz4 ◴[08 Sep 25 12:57 UTC] No.45167691[source]▶
They can regurgitate explanations as well as code. I'd strongly recommend doing actual research: you'll find better (less-distorted, better laid out, more complete) explanations.