If Anthropic’s move is confirmed, my guess is other coding agents providers might end up making similar moves

Flagging this: that’s fascism.

I wish they stopped adding features, especially useless UI “improvements” and AI stuff nobody asks for, and focused on making the system rock solid as we’re used to.

On the other hand, teaching the model to be unsure and ask questions, requires the training loop to break and bring a human input in, which appears more difficult to scale.

Not until you start mass-producing fake photos, fake videos, fake audios, put all of it into social media, shake shake shake.

It’s funny, because for me is quite the opposite: I find myself reading Python more easily when there are type annotations.

One caveat might be: for that to happen, I need to know that type checking is also in place, or else my brain dismissed annotations in that they could just be noise.

I guess this is why in Julia or Rust or C you have this stronger feeling that types are looking after you.

(They are probably “useful” in the dissemination of what the real essence of computation can reduce to, in practical terms.)

Not everything needs to be useful in fact: certain things can be just enjoyed in their essence, just looked at and appreciated. A bit like… art?

I am implementing my own Scheme as well. Why? I don’t know, one needs to do things that serve no apparent purpose, sometimes.