Hacker News: foldr

New comment by foldr in "An Uncomplicated Man – A review of The Odyssey, directed by Christopher Nolan"

foldr — Sat, 01 Aug 2026 08:57:47 +0000

Right, that was my understanding, but it seems inconsistent with what I quoted from the review.

New comment by foldr in "Golang proposal: container/: generic collection types"

foldr — Sat, 01 Aug 2026 08:51:38 +0000

It’s the same principle as accessibility. We are all poor programmers sometimes, just as we are all impaired in various ways at times even if we don’t have a disability.

New comment by foldr in "Zig's Incremental Compilation Internals"

foldr — Wed, 29 Jul 2026 09:16:58 +0000

You can easily use arena allocation in a GCed language. With modern GCs there's not usually much performance benefit, so it tends to be limited to hot paths.

New comment by foldr in "An Uncomplicated Man – A review of The Odyssey, directed by Christopher Nolan"

foldr — Tue, 28 Jul 2026 10:19:42 +0000

> The Homeric epic was already an adaptation. The poem used a relatively new technology – the written alphabet – to rework existing mythical traditions [...]

Can someone explain this one? I understand that 'The Odyssey' as a canonical work of literature can't predate the alphabet. But what she writes here makes it sound as if the written poem is just a loose adaptation of existing mythical traditions. I thought the consensus was that the poem had existed in a reasonably fixed form as part of an oral tradition prior to being written down (and that this is why it contains various features making it easier to memorize).

New comment by foldr in "Claude Code uses Bun written in Rust now"

foldr — Mon, 20 Jul 2026 23:44:22 +0000

You're right that I haven't spent much time thinking about why a project that I'm not involved with, and that is of only moderate general importance, has decided to switch from one programming language to another. Anyone who's convinced themselves that this is all part of some elaborate scheme is almost certainly overthinking it.

New comment by foldr in "Claude Code uses Bun written in Rust now"

foldr — Mon, 20 Jul 2026 14:56:34 +0000

The simplest explanation is that the Bun team decided to try rewriting Bun in Rust because they had some frustrations with Zig. I haven't seen any evidence that there's more to it than that. It's easy to get sucked into all the internet drama, but that only exists because Zig's author lost his cool and wrote a salty blog post, not because of any conniving on Athropic's part.

New comment by foldr in "Claude Code uses Bun written in Rust now"

foldr — Mon, 20 Jul 2026 12:15:40 +0000

Is anyone else failing to understand all the internet drama surrounding this?

The rewrite may work out on a technical level or it may not. Let's wait and see. The Bun project did not swear a blood oath to use Zig forever, and it's ultimately their choice to switch to a different programming language.

Beyond that, people seem to be incredibly emotionally involved with this, for reasons that entirely escape me.

New comment by foldr in "WTF: UK Police Tell Citizens to Run, Hide, and Hope [video]"

foldr — Sat, 18 Jul 2026 19:42:05 +0000

Even in Freedomland most people don't carry firearms. What else are you realistically going to do if someone has a gun except run or hide? This seems like a total non-story. Especially in a country with ~30 firearms homicides per year (which is about 1% of the per capita rate in the US).

New comment by foldr in "How I use HTMX with Go"

foldr — Wed, 15 Jul 2026 18:50:05 +0000

That’s interesting, thanks. I agree that with all those extra protections enabled, there is no security issue.

New comment by foldr in "How I use HTMX with Go"

foldr — Wed, 15 Jul 2026 14:53:51 +0000

Will it not need unsafe-eval, though? It still creates the potential for HTML injection to lead to execution of untrusted code. Execution of untrusted code is the real issue, regardless of exactly how that code ends up being evaluated and executed. Even if Hyperscript were to have its own interpreter (so that it didn't even need unsafe-eval), you'd still have the same fundamental vulnerability (unless you add nonces, or some such).

>the risk from Hyperscript is not greater than any other JavaScript in the application.

This is not really the case. If all of your client-side code is loaded via