← Back to context

Comment by troupo

8 hours ago

> Instead of simply saying 'implement themes in my product' you need to be specific, in fact more specific than usual.

Around February you could get away with very vague prompts to Claude. I feel like models have regressed since

9 comments

troupo

Reply
Bluestein  7 hours ago

Feb/April was peak for code.-

  • disgruntledphd2  7 hours ago

    Wasn't this during the period where they had a bunch of bugs around caching and the models were making loads of weird decisions?

    I honestly feel like basically nobody knows anything about these models, it's all just vibes (and I'm no different).

    • troupo  7 hours ago

      Anthropic broke their models in spring, denied it, gaslighted everyone who said so, and then all but admitted it: https://www.anthropic.com/engineering/april-23-postmortem (basically doing Anthropic things).

      > I honestly feel like basically nobody knows anything about these models, it's all just vibes

      This, too. Since only providers know what they actually serve, what they change and what limits they impose.

      There are some visible degradations though. E.g. Claude-ish.

      As for a personal anecdote: around February I created a rather complex quiz web app for myself and friends with multiple question types, sync between screens, multiple media upload types, multiple scoring and timing types, MC inetrface etc. etc. etc. It took me a week or so in the evenings with rather vague prompts to make it.

      Now Claude (and Codex) cannot reliably build a much simpler web app even with precise instructions while also maintaining the visual consistency.

      But I will agree with you, it's a feeling, not a precise measurement.

      1 reply →

globular-toast  7 hours ago

Probably because you were impressed by whatever it produced to fill in the gaps at the time. But if you expect the models to read your mind you're going to have a bad time.

  • troupo  7 hours ago

    I constantly do various greenfield side projects for myself and friends.

    I feel like need much more precise instructions much earlier in the process now than when I was building in February.

gps372  7 hours ago

Actually this was a real incident around the end of Feb this year when we had just started experimenting with spec driven development (SDD).