This is what it’s about: the forked project was NOT clear about the relationship to the original.

If the writer of this post wants people to oppose it, they really should do a better job of explaining at the very top what "it" is.

There may be good reasons to learn or not to learn calculus, or literary theory, or anything else, but the existence of some related technology isn't it. I'd go so far as to suggest that perhaps calculus is even more important for some folks to learn in the age of AI (e.g. applications in neural networks), and we don't know who those folks will be in advance.

Reading this makes me a little misty-eyed and I miss my solid old Thinkpads from 10-20 years back.

> Let models talk to each other directly, making their own case and refining each others’ answers. Exemplified in patterns like Multi-Agent Debate, this is a great solution for really critical individual actions. But XBOW is basically conducting a search, and it doesn’t need a committee to decide for each stone it turns over whether there might not be a better one.

In general, this seems reasonable to me as a good approximation of what works with humans, but with _much_ faster feedback loops in communication.