Hacker News: lantry

New comment by lantry in "Small Models Have Arrived"

lantry — Thu, 27 Aug 2026 19:18:35 +0000

The model doesn't have to be smart if all it's doing is pushing a few different buttons.

I don't have to be an automotive engineer to start my car and put it in drive.

New comment by lantry in "Changes to Sourcehut's terms of service regarding LLMs"

lantry — Thu, 27 Aug 2026 11:23:05 +0000

> The new terms of service, which will go into effect for new projects after the usual two week notice period (i.e. September 10th), will now include the following under the list of prohibited content:

> - original content written with or which facilitates the use of LLMs (large language models) or other generative AI technologies

> The use of LLMs or other generative AI tools to produce or assist with the production of source code, assets, tickets, emails, and so on, will no longer be permitted on SourceHut once these terms take effect.

> As with our other policy changes, the intention is to roll this out slowly and thoughtfully. Each possible violation will be evaluated on a case-by-case basis and we are open to making exceptions.

New comment by lantry in "Fable and the end of the free lunch"

lantry — Mon, 24 Aug 2026 10:52:06 +0000

Users have the option of silent/automatic degradation or a complete halt. I have it set to stop rather than degrade because I want to know when I've hit the safeguard.

From the claude settings:

> Switch models when a message is flagged

> When safeguards flag a message, automatically switch to a different model to keep chatting. When off, your session will pause instead. Applies to web and remote sessions.

FWIW I get a ton of usage out of fable and it's only happened to me once.

New comment by lantry in "I’m leaving OpenAI to build telepathy"

lantry — Wed, 05 Aug 2026 19:05:21 +0000

- telepathic communication with your computer

- still annoyed by AI-speak

What a bold vision!

New comment by lantry in "Pi's Minimalism Is Its Advantage"

lantry — Wed, 05 Aug 2026 13:55:08 +0000

Is there a meaningful security difference between curl-pipe-bash and cargo install --git? Couldn't the cargo install include a buildscript that jumps right into a shell?

New comment by lantry in "How is the Bun rewrite in Rust going?"

lantry — Mon, 27 Jul 2026 14:41:24 +0000

Any comment on the costs estimated in the article? especially the buildkite costs?

New comment by lantry in "OpenAI and Anthropic unite against open-weight AI risks to their bottom line"

lantry — Thu, 23 Jul 2026 13:42:36 +0000

I think axios has always used this style

New comment by lantry in "I Inspected My Take-Home Interview Project. It Was a Whole Operation"

lantry — Wed, 22 Jul 2026 21:54:24 +0000

> Side note: Why use a raw IP address? If anything, this screams “malware.” At least register a decoy domain like lint-checker.com or jenkins-ci-runner.net. If the threat actors who wrote this are reading: take notes people!

Maybe they don't want to give any identifying info to the domain registrar? Or just minimizing their online presence?

New comment by lantry in "Show HN: A self-running space economy SIM in Rust and Bevy"

lantry — Wed, 22 Jul 2026 10:58:45 +0000

right, I guess what I mean is that in the past you would pick an architecture based on your data structure/flow, performance requirements, things like that. Now there is a new metric: how LLM-friendly it is. Probably it won't be a huge factor, since a properly structured REST server would also be friendly enough, and LLMs are getting better. Still interesting to consider though, IMO.

New comment by lantry in "Show HN: A self-running space economy SIM in Rust and Bevy"

lantry — Wed, 22 Jul 2026 10:55:23 +0000

yeah it does fine with bevy. It struggles a bit to structure the components in the best way, so that still requires some human oversight if you want it to be good. It helps a lot to emphasize that you want "idiomatic" bevy code, and ofc it also helps a lot to spend a lot of tokens on design and review (e.g. "is this the most elegant way to structure these systems/components?"). There's also this feature called Bevy Remote Protocol which allows inspecting bevy state via HTTP, which really helps agents debug things. I had claude add a little wrapper that also allows injecting mouse/keyboard events and triggering a screenshot write to disk, and now claude can drive the whole game, which helps it verify things end to end.

I can't really comment on the performance. I haven't noticed any performance issues for the things I'm doing.

New comment by lantry in "Show HN: A self-running space economy SIM in Rust and Bevy"

lantry — Tue, 21 Jul 2026 21:04:41 +0000

I have also been using LLMs (mostly claude code) to develop a game with Rust and Bevy, and it seems to work very well. The strictness of rust seems to really help them get the code right, and the ECS architecture seems to make it easy for them to reason about how things work (because they only need to hold a few systems and components in context at a time).

makes me wonder if ECS will ever catch on outside the gaming industry. not sure if it's really the right architecture for web SAAS. Might be interesting to rewrite some big piece of software with ECS.

New comment by lantry in "Nativ: Run frontier open models locally on your Mac"

lantry — Mon, 20 Jul 2026 20:19:49 +0000

I think they're saying that they _had_ written the copy themselves, but were using the clanker for other tasks, and it kept going off course to "improve" the copy.

The Truth About AI's Water Use

lantry — Fri, 17 Jul 2026 17:19:07 +0000

Article URL: https://www.theatlantic.com/technology/2026/07/how-much-water-data-centers-use/687934/

Comments URL: https://news.ycombinator.com/item?id=48949807

Points: 1

# Comments: 0

New comment by lantry in "Generative AI is an Engineering Disaster"

lantry — Thu, 16 Jul 2026 01:45:54 +0000

Gift link: https://www.theatlantic.com/technology/2026/07/generative-ai...

New comment by lantry in "Duskers, the scary command line game, is getting a sequel"

lantry — Wed, 15 Jul 2026 20:11:24 +0000

Duskers is a very cool game. It's very difficult and stressful, so it's easy to bounce off of; but the concept and execution are top notch.

New comment by lantry in "Germany maybe found a new source of renewable energy"

lantry — Wed, 15 Jul 2026 13:59:05 +0000

Title makes it sound like a new method of generating energy was discovered, but really the article is about using geothermal in a new location.

> The development of medium-deep (>400 m) and deep geothermal reservoirs (> 1,500 m) could be a partial solution to provide renewable heat to single buildings, residential or commercial neighbourhoods, or districts of the city of Aachen via the existing district heating network.

New comment by lantry in "Control the Ideas, Not the Code"

lantry — Mon, 13 Jul 2026 14:53:07 +0000

I think "idea" is getting overloaded here. The article isn't talking about new feature/product/tool ideas, but about what concepts to use to build those features. e.g. what data structures and algorithms to use.

So your last line agrees with the article, I think. They are saying that it's still important to curate ideas, and no longer important to read the code; the time you would have spent reading the code should be spent curating ideas.

New comment by lantry in "The US Government Is Now a Shareholder in 26 Companies"

lantry — Thu, 02 Jul 2026 18:05:53 +0000

It creates a lot of perverse incentives, and is probably a bad idea in the long run. If the govt makes more money when intel is successful, then the govt is incentivized to sabotage Intel's competitors (e.g. through tariffs, export controls, and many other powers). This distorts the free market that is (allegedly) at the center of America's success

New comment by lantry in "U.S. allows Anthropic to release Mythos AI to ‘trusted’ US organizations"

lantry — Sat, 27 Jun 2026 14:34:04 +0000

"there are in-groups that the law protects but does not bind, and out-groups that the law binds but does not protect"

i.e. freedom for me but not for thee

New comment by lantry in "Apple raises prices of MacBooks, iPads"

lantry — Thu, 25 Jun 2026 20:04:03 +0000

If you wanted to be realistic, you wouldn't say for sure that they won't.