Hacker Newsnew | past | comments | ask | show | jobs | submit | boutell's commentslogin

Halfway through I was imagining aliens to whom this operator comes naturally and our math is weird. By the end I found out that we might be those aliens.

I love this! Dijkstra's Algorithm is always a fun time

I do love Disjkstra :) this actually uses a modified version of the "Raptor" algorithm for public transport routing (hence the name!): https://www.microsoft.com/en-us/research/wp-content/uploads/...

I've been busy adding postgres and sqlite support to apostrophecms:

https://apostrophecms.com

Six months ago, that would have been unrealistic, because we're heavily committed to the mongodb API and we make it part of our own API.

Starting in December though, Opus 4.6 made it perfectly realistic to pursue this with Claude Code as a series of personal weekend projects.

Now, despite not having any official resources on this until the last week or so, it should land in May.

This doesn't work for everything. It absolutely helps that the problem I'm solving is an "adapter pattern" problem: "make X talk like Y." And that we have a massive test suite, at multiple levels. That combination makes "here's the problem, go solve it, grind until the tests pass, don't bother me for a few hours" a realistic AI agent request.

But it's a little mind-blowing all the same. The hype around AI is so out of control, it can be easy to miss genuine "holy crap" moments.

Along the way I've written a fair bit about how to run Claude Code autonomously on your household server in a reasonably secure manner:

https://apostrophecms.com/blog/how-to-be-more-productive-wit...)

Also general Claude Code tips and thoughts on workflows that help and workflows that ultimately just speed your burnout:

https://apostrophecms.com/blog/claude-code-part-2-making-the...

I know, everybody's writing this stuff, but the desire to share is natural.

(Disclaimer: I'm part of the demographic AI was trained on. If I tried not to sound like a bot, I'd have to sound like... well, somebody else)


Correct link:

https://pages.awscloud.com/aws-reaction-ai-space-orbit.html

I don't know how this gets messed up every time I try to share it here.


AWS just dropped this blog post describing the glories of AI data centers in space.

Most companies hyping this ignore the cooling problem: in space, you only have radiative cooling to rely on. Even though the temperature outside is absolute zero, radiative cooling is so inefficient that getting rid of heat is a major engineering requirement for every spacecraft.

But AWS is doubling down. They describe "natural cooling through radiators that dissipate heat into an environment hovering around minus 270 degrees" as a BENEFIT of space-based Ai datacenters.

Obviously, AWS engineers are smarter than this. And AWS is a solid business with a future, AI or no AI.

So why does AWS, a credible company with an established reputation, feel the need to echo the hype? Is there anyone left who doesn't know this is greenwashing?

[Reposted due to bad link in my original post]


"The vacuum of space provides natural cooling through radiators that dissipate heat into an environment hovering around minus 270 degrees..." This is not how physics works. The lack of convection in space makes cooling harder, not easier. This isn't the only nonsense in the article but it's the worst part. How do we make it prohibitively embarrassing for companies to keep making this claim that AI data center cooling in space will just magically work?


"The vacuum of space provides natural cooling through radiators that dissipate heat into an environment hovering around minus 270 degrees..."

This is not how physics works. The lack of convection in space makes cooling harder, not easier. This isn't the only nonsense in the article but it's the worst part. How do we make it prohibitively embarrassing for companies to keep making this claim that AI data center cooling in space will just magically work?


Whoops thanks, made a fresh post.

I found the article itself very informative and not particularly ai-tastic. But then I got to that infographic at the end. Holy smokes was that disappointing. It seems clear they didn't even bother to read the captions the AI scribbled.

Last night I had to install the VO.20 pre-release of ollama to use this model. So I'm wondering if these instructions are accurate.

That's interesting man, that's pretty f***' interesting. I don't think I've seen it though. I've let it run for hours making changes overnight and I only do git operations manually.

Oh, but maybe allowing it to do remote git operations is a necessary trigger.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: