Hacker News: chris_st

New comment by chris_st in "FrontierCode"

chris_st — Mon, 08 Jun 2026 23:59:00 +0000

What "non-house" harnesses have you found to work best?

New comment by chris_st in "Tribute to Jiro Yamada, Automotive Artist (1960-2025) [video]"

chris_st — Sat, 06 Jun 2026 17:59:01 +0000

Interesting to see (roughly!) what percent of each car is engine.

New comment by chris_st in "Using Tailscale with an OrbStack VM on macOS"

chris_st — Thu, 28 May 2026 20:36:57 +0000

I have this setup, roughly, with UTM rather than orbstack. I think I have it set up safely, curious how you see it has the wrong permissions?

New comment by chris_st in "Using AI to write better code more slowly"

chris_st — Tue, 26 May 2026 12:45:40 +0000

Another way I'm "going slower" is to have the AI implement individual sub-steps of the current task, and review each one. It's slower than having it yolo out the whole thing, but it's much smaller incremental bits to review, so my brain doesn't glaze over in a huge review, like I had if I had it do the whole task.

I'm following an Ideas -> PRD -> Issues -> Tasks methodology, where each task has a bunch of sub-tasks. I have it just do one (or a few, I'm having it do Red/Green/Refactor as separate sub-steps, so I review the Red case, and then once that's good, do the Green and Refactor steps, and review those).

New comment by chris_st in "Using AI to write better code more slowly"

chris_st — Tue, 26 May 2026 10:27:59 +0000

Yup, just like people!

New comment by chris_st in "Using AI to write better code more slowly"

chris_st — Tue, 26 May 2026 10:27:12 +0000

Good!

New comment by chris_st in "What the Hell Was Going on with Cigarette Ads in the 70s? (2024)"

chris_st — Thu, 14 May 2026 09:17:47 +0000

Nope, not better quality if you don't like the smell of cigarettes.

New comment by chris_st in "Show HN: Statewright – Visual state machines that make AI agents reliable"

chris_st — Tue, 12 May 2026 22:52:00 +0000

Please add support for the Windsurf editor as well. Thanks!

New comment by chris_st in "What we lost the last time code got cheap"

chris_st — Sat, 09 May 2026 19:16:20 +0000

Awesome, stealing that!

New comment by chris_st in "Bun's experimental Rust rewrite hits 99.8% test compatibility on Linux x64 glibc"

chris_st — Sat, 09 May 2026 19:02:12 +0000

And they're clearly marked as `unsafe`, so easy to find, which gives them a nice list of issues to address.

New comment by chris_st in "What we lost the last time code got cheap"

chris_st — Fri, 08 May 2026 20:16:48 +0000

I asked Claude to tell me why something was implemented the way it was, and got an excellent response. One data point, would love to hear more examples.

New comment by chris_st in "Where the goblins came from"

chris_st — Thu, 30 Apr 2026 12:11:35 +0000

...it came as a surprise that [leaving a Petri dish out with a window open] would end up with interesting [molds] (called [penicillin]). _It was not planned at all_.

New comment by chris_st in "Lambda Calculus Benchmark for AI"

chris_st — Sat, 25 Apr 2026 15:53:26 +0000

Well, to be fair, people cheat by remembering what they did last time. I think the idea here is to run the models from a "clean slate" and see how often they succeed/fail.

They are, like people, non-deterministic, so giving them several "fair" trials makes sense to me.

New comment by chris_st in "Google Plans to Invest Up to $40B in Anthropic"

chris_st — Fri, 24 Apr 2026 20:52:24 +0000

Possibly because they just haven't been able to manufacture enough of them yet to be a viable business to others? They're fighting everyone else for foundry space and time.

New comment by chris_st in "Assessing Claude Mythos Preview's cybersecurity capabilities"

chris_st — Thu, 09 Apr 2026 21:58:57 +0000

But it's pretty cool that LLM bug hunting is pretty cheap... the 1-person projects can do it themselves, don't have to contract out to some huge security company.

New comment by chris_st in "Assessing Claude Mythos Preview's cybersecurity capabilities"

chris_st — Tue, 07 Apr 2026 21:10:31 +0000

Well, maybe not... see Simon Willison's ongoing reporting [0] on all the bug reports for `curl` people are finding with LLMs.

Interesting to see them go from "DON'T GIVE US AI SLOP!" to "Wow, lots of actual bugs found, including [ed: at least one] bug found by two people!"

[0]: https://simonwillison.net/search/?q=curl

New comment by chris_st in "Tailscale's new macOS home"

chris_st — Fri, 03 Apr 2026 15:46:03 +0000

From the article:

> As we noted at its September beta release, a windowed version of Tailscale’s macOS app doesn’t replace the menu bar app, but runs alongside it. It can be pulled up from the Dock or a Spotlight search, and makes a lot of Tailscale data and features more accessible.

New comment by chris_st in "CodingFont: A game to help you pick a coding font"

chris_st — Mon, 30 Mar 2026 19:43:15 +0000

Seconding Maple Mono - it's very nice.

New comment by chris_st in "Anthropic drops flagship safety pledge"

chris_st — Thu, 26 Feb 2026 13:27:55 +0000

Just out of curiosity, which version of Claude?

New comment by chris_st in "What podcasts are you listening to?"

chris_st — Thu, 26 Feb 2026 13:24:18 +0000

Good nerd stories, alas it was cancelled, so no new ones:

- Uncharted with Hannah Fry

Some great fiction:

- Achewillow - horror, but not excessively horrible.

- Desert Skies - humor, about folks who work in the first sphere of the afterlife, folks who are recently dead and arrive in Buick Skylarks are equipped with microwaveable burritos and information about the spheres to come.

Fantastic poetry:

- Poetry Unbound

Really fantastic interviews, alas, it's no longer updated:

- Partners by Hriskikesh Hirway

Linguistics and language:

- The Allusionist

Tabletop RPG:

- My First Dungeon