I am just lost. I wanna watch a documentary on how this kind of thing gets thought out and made and approved by a lot of people and then comes to being annouced as an actual hardware product.

Maybe let's take Langsmith. Now I know my gripes with that product. How do you see it? What do you add, specifically?

How does it handle unknown queries?

In practice, Claude is trained on its harness and the subscription is priced to best competitors such as Cursor.

This is also why Cursor tries to finetune oss models. Otherwise its performance in the CC flavor of AI coding will just be that bit worse

What you mention as advantages and features is not something CC users use or require.

On the other hand, Claude is trained on its harness (all but confirmed by Anthropic) so CC is likely just a bit better at its level of abstraction than in cursor. And at the end, you can’t yet best the subscription.

And then, compared to China, the US acts overtly hostile: threatening us with war, starting a war in order to collapse energy supplies outside of the US. Opportunistic beyond even China, much more hostile.

Will the US even be a democracy in two years? Is it now?

Nah man, balancing between China and the US is the only thing a smaller country can do in order not to be crushed

This one seems weird

Cursor was the tool you use to pair program with AI. Where the AI types the code, and you direct it as you go along. This is a workflow where you work in code and you end up with something fundamentally correct to your standards.

Claude Code is the tool you use if you want to move one abstraction layer up - use harness, specs, verifications etc. to nail down the thing such that the only task left is type in the code - a thing AI does well. This is a workflow where the correctness depends on a lot of factors, but the idea is to abstract one level up from code. Fundamentally, it would be successful if you don't need to look at code at all.

I think there is not enough data to conclusively say which of these two concepts is better, even taking into account some trajectory of model development.

I do feel that any reason I have for installing Cursor is that I want to do workflow 1, rather than workflow 2. Cause I have a pretty comprehensive setup of claude code (or opencode, or whatevs) and I think it does everything you list here.

So, as a product engineer, you probably wanna mention why it matters that Cursor UI allows you to edit files with auto-complete.

That's basically it. You can review changes afterwards, but that's not the main point of Claude Code. It's a different workflow. It's built on the premise: given a tight and verifiable plan, AI will execute the actual coding correctly. This will work, mostly, if you use the very best models with a very good and very specific harness.

Cursor, same as Copilot, has been used by people who are basically pair programming with the AI. So, on abstraction down.

I have no idea what is better, or faster. I suspect it depends at least on the problem, the AI, and the person.

However, is this really a moat?

And also we know why: effective context depends on inout and task complexity. Our best guess right now is that we are often between 100k to 200k effective context length for frontier, 1m NIHS type models

Any national worlds book list, and this explicitly includes US and UK lists, are heavily skewed and I mean ridiculously so

I think there are also licenses that do that, and revert to full MIT after some time, but the author decided to roll their own.

What’s the problem with that? He can license it however he wants and the reason he mentions is perfectly valid tbh