Hacker News: thurn

New comment by thurn in "MTG Bench: Testing how well LLMs can play Magic"

thurn — Fri, 12 Jun 2026 02:17:55 +0000

To clarify, the more accurate description would be "Testing how well LLMs can follow the rules of Magic", right? There is no actual evaluation of how "well" they are playing?

New comment by thurn in "Americans don't know how to fight AI so they're fighting data centers"

thurn — Tue, 02 Jun 2026 16:46:38 +0000

This is basically just the normal dynamic with American tax law where tax jurisdictions are terrible at coordinating, so they end up approving things and agreeing to tax things at a very low level in order to win the competition. Even when states/counties try to work together on this stuff there's a huge defector problem, like "hey I can back out of this multistate tax compact agreement and get 500 new jobs which will let me win local reelection".

I suppose you can reduce a lot of both good at bad things about the country to "because federalism".

New comment by thurn in "What Is Date:Italy?"

thurn — Mon, 18 May 2026 16:16:44 +0000

I wonder how Paradox handles this stuff in their games like Europa Universalis. Have they ever made a "the pope wants you to switch calendar systems" event which changes the actual in-game date?

New comment by thurn in "Welcome to Gas City"

thurn — Mon, 04 May 2026 21:41:30 +0000

I really fundamentally do not understand what problem Gas City solves that is not already solved by normal subagent orchestration patterns. If you want to call your main LLM session the "mayor" and have it delegate its work out to planners and coders and reviewers and QA and so on, this is already a thing you can do! If you want to do this in a reusable way you can create skills and subagent definitions and use /commands, etc. Why do we need hundreds of thousands of lines of opaque Go code to accomplish any of this?

New comment by thurn in "Excessive token usage in Claude Code"

thurn — Sat, 21 Feb 2026 05:22:23 +0000

There's a real hobbyist vs professional distinction with Claude Code. For professionals, including when I use it at work, we're generally super happy to have Claude spawn as many subagents as possible and burn more tokens to get a better result. Hobbyist users on a $20/month plan, though, generally want more conservative behavior.

It's hard for Anthropic to cater to both sets of users with one model.

New comment by thurn in "Apple M5 chip"

thurn — Wed, 15 Oct 2025 13:28:51 +0000

No "max" or "pro" equivalent? I wanted to get a new Macbook Pro, but there's no obvious successor to the M4 Max available, M5 looks like a step down in performance if anything.

New comment by thurn in "GPT-5-Codex"

thurn — Tue, 16 Sep 2025 12:22:45 +0000

Does the "caching containers for Codex Cloud" mean I have some chance of being able to reuse build artifacts between tasks? My Rust project takes around 20 minutes to set up from scratch in a new Codex environment, which seems extremely expensive.

New comment by thurn in "Claude is the drug, Cursor is the dealer"

thurn — Mon, 11 Aug 2025 18:50:57 +0000

I think Cursor tab-completion is entirely in-house, right? That feature on its own is worth at least $5/month, it's super well done.

New comment by thurn in "Ozempic shows anti-aging effects in trial"

thurn — Tue, 05 Aug 2025 18:30:02 +0000

Are we close to having generic semaglutides e.g. available in India? Or locked into high prices for the foreseeable future?

New comment by thurn in "Evolving OpenAI's Structure"

thurn — Tue, 06 May 2025 04:49:15 +0000

Which of these statements do you disagree with?

- Superintelligence poses an existential threat to humanity

- Predicting the future is famously difficult

- Given that uncertainty, we can't rule out the chance of our current AI approach leading to superintelligence

- Even a 1-in-1000 existential threat would be extremely serious. If an asteroid had a 1-in-1000 chance of hitting Earth and obliterating humanity we should make serious contingency plans.

Second question: how confident are you that you're correct? Are you 99.9% sure? Confident enough to gamble billions of lives on your beliefs? There are almost no statements about the future which I'd assign this level of confidence to.

New comment by thurn in "Show HN: BugStalker - a modern Rust debugger"

thurn — Fri, 25 Apr 2025 19:45:56 +0000

is this necessarily linux for dependency reasons, or could it be on OSX in the future?

New comment by thurn in "An image of an archeologist adventurer who wears a hat and uses a bullwhip"

thurn — Fri, 04 Apr 2025 14:40:14 +0000

Also copyright duration when Star Wars was created was a maximum of 56 years, and obviously George Lucas felt that was sufficient incentive to create it!

New comment by thurn in "Oxygen discovered in most distant known galaxy"

thurn — Thu, 20 Mar 2025 23:44:05 +0000

this doesn't seem to provide much of a justification for an extraordinary claim like "the widely accepted number for the age of the universe is wrong by 4 billion years"?

New comment by thurn in "Effective Rust (2024)"

thurn — Sun, 02 Mar 2025 18:41:32 +0000

Kind of surprised that this book could be published by O'Reilly and also freely available online? Seems unusually generous.

New comment by thurn in "Operator research preview"

thurn — Fri, 24 Jan 2025 06:08:48 +0000

hm, wouldn't you almost by definition think you were doing a good job of flagging them at any level of actual effectiveness?

New comment by thurn in "Ask HN: Teams using AI – how do you prevent it from breaking your codebase?"

thurn — Tue, 14 Jan 2025 19:05:21 +0000

If you've hired an intern before, think of Cursor like that. When you come up with an intern project plan, you usually need to give a very clear specification of what you expect, and you usually need to have the project be pretty self-contained. A lot of real problems are really bad intern projects, and a lot of problems are a really bad fit for AI. You have to be strategic about it.

New comment by thurn in "Shapez2 Released"

thurn — Tue, 20 Aug 2024 10:13:18 +0000

Liking it so far, although the 'task' progression isn't my favorite. Feels like there are way too many tasks to do that seem like tedious busywork.

Honestly a really simple game design fix for this would be to unlock tasks more slowly as the player demonstrates more engagement with the system. That way if you are like me and mostly find them boring and repetitive, you don't feel as bad about not getting them done.

New comment by thurn in "Features I'd like to see in future IDEs"

thurn — Fri, 09 Aug 2024 18:43:34 +0000

The queryable expression thing is something I struggle with all the time in Rust. It's especially bad in that language because (unlike in e.g. Java or C#) there is no way to view the Debug representation of your types in the debugger, you just get the raw memory layout which adds a huge barrier to 'what is going on with this code?' and requires you to dig around through countless nested layers to understand it.

New comment by thurn in "Supreme Court rules ex-presidents have immunity for official acts"

thurn — Mon, 01 Jul 2024 19:05:10 +0000

There is a certain amount of deliberate ambiguity to Article I Section 8 -- take a look at e.g. https://avalon.law.yale.edu/18th_century/debates_817.asp and you can see that the wording "The Congress shall have power to [...] declare war" was revised from "make war" in the earlier drafts. Madison clearly felt that Congressional authorization was on some level required to conduct a war, but that the Executive should be free to act quickly in self-defense, e.g. to repel an invasion.

New comment by thurn in "Shattered Pixel Dungeon is an open-source traditional roguelike dungeon crawler"

thurn — Thu, 21 Mar 2024 11:38:37 +0000

Interesting that this project seems to contain a bunch of sprite assets released under GPL3. How does GPL apply to something like an art asset?