Karpathy: A few random notes from Claude coding quite a bit last few weeks

Re:Karpathy: A few random notes from Claude coding quite a b... by Aurornis on Wednesday January 28, 2026 @10:00AM (#46796198)

> the meta-skill of learning to use the LLM depreciates too. Today's LLM is gonna go away someday, the way you have to use it will change. You will be on a forever treadmill, always learning the vagaries of using the new shiny model (and paying for the privilege!)

I haven’t found this to be true at all, at least so far.

As models improve I find that I can start dropping old tricks and techniques that were necessary to keep old models in line. Prompts get shorter with each new model improvement.

It’s not really a cycle where you’re re-learning all the time or the information becomes outdated. The same prompt structure techniques are usually portable across LLMs.

[ Parent | on HN ]

Re:Karpathy: A few random notes from Claude coding quite a b... by rubenflamshep on Wednesday January 28, 2026 @12:09PM (#46798204)

Interesting, I’ve experienced the opposite in certain contexts. CC is so hastily shipped that new versions often imbalance existing workflows. E.g. people were raving about the new user prompt tools that CC used to get more context but they messed my simple git slash commands

[ Parent | on HN ]