HN user

WaterRun

13 karma
Posts4
Comments15
View on HN

Linux’s ecosystem has also improved significantly over the past two years, especially in China. Due to the influence of “Xinchuang” (that is, domestically produced Linux rebranded under another shell), many Chinese desktop applications have been reworked in the past couple of years, switching from Windows-specific tech stacks to cross-platform ones—mostly Electron, basically browser wrappers—and now support the Linux platform. The commonly used software is basically all there.

In addition, the development of LLMs has greatly lowered the barrier to using the Linux command line. Problems that used to take a full day to solve can now be handled easily by anyone who can write a prompt—just ask, copy, and paste. This has even made Windows’ command line unfriendly by comparison, despite its own major improvements in recent years, turning it into a significant drawback.

The Space Shuttle’s technology is indeed quite old, but by today’s standards it is not exactly outdated. What matters is that we have lost the ability to carry out that technology — or even the ability to organize and coordinate a project like that. Otherwise, the price of the SLS as an “off-the-shelf product” would not be so outrageous, and it would not keep getting delayed again and again. Technology gets forgotten and capability is lost as people and suppliers disappear. The fact that we could build the Saturn V half a century ago does not mean we could still build it today; even the fact that we could build the F-22 twenty years ago does not mean we could still produce it now once the production lines are gone. Restoring that capability is always a good thing, considering the indirect effects.

Developing something like this would push the frontiers of human technology. Without the Apollo program, not to mention anything else, the personal computer boom in the 1970s might have been delayed by a long time.

Traditional programming requires the absolute precision provided by digital circuits; a single bit flip can lead to a completely different outcome.

Large models do not require that kind of exactness. They are somewhat like a "field" or a "probability cloud": as long as the main directional tendency is correct, a few individual deviations—or even a whole cluster of them—make almost no difference.

Is Anthropic's acquisition of Bun alone still not enough to infer their tech stack? What more obvious signals would be needed?

Also, honestly, given the speed constraints of large models, it makes almost no difference what language an agent is written in. The small performance differences between programming languages do not even begin to matter compared with network latency, let alone the speed at which a large model streams tokens.