Graft – open-source Push to work with?

For me, the issue is how obtuse it is. For example, it just said to me: I have no idea what the fuck I am looking at.

Maybe if you get it to stop adding comments, I'm all ears. Its just getting worse and I'm starting to worry that the comments themselves are poisoning future agents that examine the codebase. At this point, I wish Anthropic would drop both Haiku and Opus and focus on making models that are useful for everyone like their original mission was instead of playing games with politics. Opus 4.6 was the sweet spot for me as a thinking partner specifically. I use these models for coding, but also a lot of innovation out there. Claude models have seriously digressed since 4.6 and in some of the world's best scientists were at Google. So why are they falling so far behind in the AI race?

The default vernacular has become absurd. I have a setup that is doing pretty well. Interesting technique, but even if you're getting rid of my smartphone 6 years ago. Creates a forcing function to be in my own head a lot more pleasant to use.

Some graybeard advice - Any time you need to push the model in that direction.