←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
wg0 ◴[08 Sep 25 12:39 UTC] No.45167544[source]▶
I have used Gemeni and OpenAI models too but at this point - Sonnet is next level undisputed King.

I was able to port a legacy thermal printer user mode driver from legacy convoluted JS to pure modern Typescript in two to three days at the end of which printer did work.

Same caveats apply - I have decent understanding of both languages specifically various legacy JavaScript patterns for modularity to emulate other language features that don't exist in JavaScript such as classes etc.

replies(1): >>45167584 #
piskov ◴[08 Sep 25 12:44 UTC] No.45167584[source]▶
Check swe-bench results but for C#.

It’s literally pathetic how these things just memorize, not achieve any actual problem-solving

https://arxiv.org/html/2506.12286v3

replies(1): >>45168330 #
antonvs ◴[08 Sep 25 13:56 UTC] No.45168330[source]▶
You've misunderstood the study that you linked. LLMs certainly memorize, and this can certainly skew benchmarks, but that's not all they do.

Anyone with experience with LLMs will have experienced their actual problem solving ability, which is often impressive.

You'd be better off learning to use them, than speculating without basis about why they won't work.

replies(1): >>45168729 #
piskov ◴[08 Sep 25 14:27 UTC] No.45168729[source]▶
What exactly did I misunderstand?

Also “learn to use them” feels you’re holding it wrong vibes.

See also

https://machinelearning.apple.com/research/illusion-of-think...

replies(2): >>45168831 #>>45178324 #
1. wg0 ◴[08 Sep 25 14:34 UTC] No.45168831[source]▶
You did not misunderstand anything. Sure, LLMs have no cognitive abilities. So even with widely used languages, they do hit the wall and need lots of hand holding.