But as someone who came of age in the AIM / ICQ / IRC days, it feels pretty normal. That's just how we wrote. I still fall into it by accident when the context is right and I'm not thinking about it (eg Slack at work). I hope youngsters aren't judging me for it.

Good chance it's not real or misdiagnosed. But it gives me some degree of schadenfreude to see it happening to the Claude Code repo.

> Ah, APL/J/K. Time for my annual crisis of thinking everything I've ever learned about programming is wrong...

Still, though, I'm always happy when it comes up on HN for a little discussion. As I recall there were a couple people working on a new OS or something based on K, I think. I wonder whatever happened to that.

As for this particular post, I get how `x^x*/:x:2_!100` works now (it's cute!), but it seems pretty wasteful. It's generating 10,000 products to filter out of the list of 100 integers. But 99 x 99 isn't anywhere near a number in the original 2..100 list! You only need to go up to 2 x 49, 3 x 33, etc. I wonder if there's more of a "triangular" shape you could generate instead of the full table.

[0] https://x.com/losvedir/status/636034419359289344?s=20

This only works for people using agents themselves on computers they control, rather than, e.g., the Claude web app, but is a good chunk of my usage.

I think people are either over or under thinking the auth piece, though. The agent should have access to their own token. Both CLIs and MCPs and even raw API requests work this way. I don't think MCPs provide any further security. You should assume the agent can access anything in its environment and do everything up to what the credential permits. You don't want to give your more powerful credential to the MCP server and hope that the MCP server somehow restricts the agent to doing less (it can probably find the credential and make out-of-band calls if it wants). The only way I think it could work like that is how... is it Sprite does it?... where you give use a fake token and have an off-machine proxy that it goes through where it MitMs the request and injects the real credential.

The Navy is performing well at the things it's being tasked with because it's only being tasked with things it can do well! But I think the point of this thread is that it still reflects poorly on the Navy if those things aren't actually useful in this war. They say generals are always preparing for the previous war and perhaps that's happening here.

As I was reading the post I was wondering along the same lines, if this is different from before. Going to space is an inherently risky activity. It's always going to be easy to write the "this is not safe" think piece, where you can either say "I told you so" or "Whew, thankfully we made it this time!" afterwards. Things like this only happen when you accept some risk and people say "yes" press forward.

All that said, not all risk is equal, and I'm trying to understand if NASA is uniquely dysfunctional now and taking needless, incidental risks.

Oh, God, why you gotta do us like that?

Oh, wait.

I'm probably really out of date at this point, but my impression was that fine tuning never really worked that well for knowledge acquisition, and that don't variety of RAG is the way to go here. Fine tuning can affect the "voice", but not really the knowledge.