adastra22

And his name, if you need glasses like me, looks like AI slop.

Claude code still can’t handle scrolling history without corruption. It is embarrassingly broken.

No.

You can run open weight models anywhere.

We aren’t there yet. Not for frontier development work at least.

I get what you're saying, but these instances are of a different type. It is along the lines of "if I pass None for this parameter, will it default to X or return an error?" and it looks, but finds that the actual logic is distributed across multiple files. And so it quickly falls down that rabbit hole.

All the while, it could have just done a two-line probe test and see what happens when it calls the API with "None" for that parameter. Or just assum it would act as expected and wire in debug logs in case it doesn't.

I need the full context window to get the work done though.

The curiosity is inefficient though. So many times I have to stop the agent and tell it to just fucking write the code and try compiling it. Otherwise it will fill its entire context tracing through the program logic to derive from the code itself whether the thing it is about to do would work. It completely fails to notice it can just… try.

--disallowedTools Task

Everything, when other options are available? The strongest argument for Typescript is that it isn’t JavaScript, which doesn’t apply here.

“Physical chemistry” is the search term for what you’d be interested in.

General physics and chemistry take different approaches forced by the subject matter. Physics abstracts to problems over concepts with details abstracted away, but at higher levels of education you learn to apply these corrections.

Chemistry starts with practical reality and a lot of rote memorization. Only at the higher levels do you get the unifying theory. Since the unifying theory is quantum electrodynamics (in this case, relativistic QED), that makes sense.

I have not noticed this with Opus 4.6+. The result is usually not too far from what I would have written myself.

You are not paying for silicon, lol. The cost of a chip is many, many orders of magnitude more than the raw material cost.

Why would you expect smaller transistors to be cheaper?

That’s where the name comes from, no?

No it’s not on me to explain why. I’ve just been watching this company since 2008, and seen them break ahead of the competition and then stay ahead as they move faster than anyone else. I’m saying the historical trend line has that gap widening. That’s a statement of fact, no “why” involved.

If you want to know the why’s I suggest reading Eric Berger’s two books Liftoff and Reentry.

Because year by year the gap is growing. I’m talking about a historical trend, and that’s just a fact about it. The gap has been growing, not shrinking.

Because SpaceX moves faster. I’m telling you an empirical fact: three years ago the rest of the industry was 8 years behind SpaceX. This year they are ten years beyond. The gap is widening not shrinking.

That has been how Elon always operates. It’s “green lights to Malibu” timeline estimation. He does it for a reason.

The rest of the industry is about 10 years beyond SpaceX. But note that they are where SpaceX was a decade ago, which is not the same thing as “in 10 years they will catch up.” The gap is getting larger year by year, not smaller.

The material wealth of the Earth is only a small, small fraction of the accessible material in the inner solar system, let alone the universe.

Starship fundamentally changes the game in ways people aren’t paying attention to because it pattern matches to sci-fi. But the economics are real: power and material far beyond what is available on Earth, on many cases at lower marginal price than terrestrial sources, and 1000x to 100000x reserves.

China (and others, e.g. Blue Origin and Rocket Lab) are rushing to catch up to where SoaceX was 10 years ago. They are moving faster than anyone in aerospace has ever moved before, but SpaceX is still accelerating faster than that. By the time they catch up, the game will have again changed.

SpaceX and NVIDIA share this trait. They out-innovate, and know only one speed: the speed of light. The tortoise can only beat the hare if the hare takes a nap, and nobody is napping at SpaceX.

I’m not a fanboy. I have criticisms of SpaceX. But you are pattern matching to the common story of startups getting complacent and being surpassed by up-comers in China and elsewhere. But the innovators dilemma only applies if the innovator stops innovating. Two decades on, SoaceX is still innovating as much as they always have.

Fable is consumer-branded Mythos.

This is my industry I know it well, apparently much better than these bozos. SpaceX launch is only “unprofitable” only in the accounting sense because they reinvest their profits into Starship. Their actual profit margin for launch of F9 is 62% - 80% depending on configuration. That is a margin unheard of in aerospace.

There is literally no competition worth speaking of, and nobody to provide downward price pressure. SpaceX started moving into their own constellations because lower prices open up new markets, and this lets them access those markets without having to lower launch prices.

And if you think, as Morgan Stanley seems to, that the only money to be made in space is selling launch of earth orbiting satellites, you’re going to miss out on the boom that is going to make the first quadrillionaire.

This feels like the “there’s a global market for maybe 4 computers” of the 21st century.

SpaceX’s launch services have huge margins.

He3 is needed as a cryogenic for quantum systems, not fusion fuel.

Because.

We are literally creating won’t right now.

What feature is that?