[edg5000]

Nonsense indeed. The model knowledge is the current state of the art. Any computation it does, advances it. It re-ingests work of prior agents every time you run it on your codebase, so even though the model initializes the same way (until they update the model), upon repeated calls it ingests more and more novel information, inching the state of the art ever forwards.

[JackSlateur]

Current state of the art ? You must be joking .. I see code it has generated, some interns does better.

Obviously, you are also joking about the thing that AI is immune to consanguinity, right ?

[edg5000]

I've seen terrible things where it would overcomplicate and duplicate. But I've also seen it write really good code. I've been trying to get it to do the latter consistently. Detailed specs and heavy use of agents really helps with the code quality. The next step is editing the system prompts, to trim away any of the fat that's polluting the context.

[simonw]

If you have had interns who can write better code than Opus 4.5 I would very much like to hire them.