← Back to context

Comment by JaggerJo

5 days ago

IMO we are reaching the point where AI models are simply a commodity. Opus (since ~4.6) is sufficient for everything I tried coding wise. I use it to write features (but I review and understand every line it spits out) and to review code.

For code review I also still review everything myself, but use Opus to catch stuff I missed and to judge if a PR is even ready for me to review.

After just updating Claude Code to the latest version I thought about picking Fable (the bigger model) instead of Opus.

But I have no reason to. Opus does everything I want it to do. It could do it faster - that would be an improvement. But for the normal stuff we reached the point where better models are not worth it IMO.

There still might be cases where you want to throw Fable at it.

3 comments

JaggerJo

Reply
FergusArgyll  5 days ago

> Opus (since ~4.6) is sufficient for everything I tried coding wise.

I don't know what that means. It seems like a lack of motivation or something. Like, if it's possible that in one day will be absolutely incredibly intelligent, surely you want to create

  - Your own browser (maybe chrome - mv3 + reading list search etc.
  - An emacs clone which has evil baked in, completely vim compatible + threaded elisp - that weird window sizing bug which only occurs on my laptop
  - An extension which completely restyles amazon.com to make it usable

It just feels impossible to ever get that, but I wouldn't say "what we have is sufficient"