chickensong

This is peak old man yells at cloud.

There's so much good radio to be had since the arrival of the internet. Not even talking about online-only, but actual radio stations who also stream. Maybe there's less cool broadcast stations in any given area, but our overall exposure via internet is incredible. Just search for free-form radio. If you have a college in your area, you probably have interesting radio and DJs on the airwaves.

The article ends with giving up, ipod + KPFA news, which just seems wild. Never has there been a time where there's more music available.

There are a lot of Muggles in the world.

Windows 3.1? It was only 6 3.5” disks.

Well ackchyually... Windows 3.1 was just a window manager, you needed another 3 disks for DOS, and if you wanted that sweet networking support, you'd need Windows for Workgroups 3.11 which was 8 disks!

It is indeed funny/sad to see the rancor created by our own inputs. You can't escape the AI police on HN right now. There will always be someone leaving a shallow complaint or accusation about the look or language, regardless of reality. Obviously slop exists, but the culture war has polarized some people enough that they're blinded, and anything resembling LLM output is a trigger. God help you if you use useful language like "load-bearing", because the police are definitely on their way.

FWIW, I don't think the site fits the LLM template. The scroll through the use cases is particularly nice.

And thanks for Elixir. I love it, and the agent + tidewave loop is a joy to use!

A portion of the leading edge is already talking to their computers. First it was wiring up Wispr to your agent, now you can just enable voice mode in Claude. That paradigm shift just hasn't reached the mainstream yet.

Most people can barely type or operate a computer, so I think it will be a boon to many folks to have a voice/agent interface to their computing. I agree that a local model that's "good enough" will suffice for most general tasks. There's no need to call Mythos to "add cheese to the shopping list" or "summarize today's emails". Harder tasks will call out to stronger models, but many people just won't need that power.

I suspect all the platforms are keenly aware of this, and Apple will drop Siri v2 or whatever when they're satisfied with their UX and more confident the agent won't go off the rails.

I enjoy some battlestation pics, but this feels like an oddly uniform collection that makes me feel like I'm looking at a stock art catalog. I'm not sure if it's a narrow demographic being interviewed, the photos themselves, the presentation, or what. It's kind of eerie.

But Anthropic is a leading company that makes cutting-edge AI which will kill people. It’s literally a matter of life and death and at this point

But Stihl makes cutting-edge chainsaws which will kill people. It’s literally a matter of life and death and at this point

So as an institution, I don’t want human answers, I want the right, most professional answers.

We deeply regret our auto-saw feature activated while you were sawing unattended. Your safety is our top priority.

HURF DURF

Does the LLM become another interface to computing?

It already is.

Very cool, thanks for the write up on the recommendations. I'm always hungry for new music and I have a somewhat patchy last.fm history going back to 2005. I'd love to check out your tool, email in profile. Cheers!

Very interesting! I'm considering Meilisearch but have zero experience with it, so I appreciate your response, thanks. I've used Elastic in the past, but trying to avoid it now. I'm a ways from needing edge distribution, so hopefully Meili might be a decent choice until then. Isolated indexing shipped back to the core sounds pretty cool though.

1. I'm interested and would like to know more! Will you be publishing it? How do the recommendations work?

Do your crawlers respect robots.txt and have a fixed IP pool that can be blocked?

Where do you get your data from?

What drove you away from Meilisearch?

Slides from DWebCamp 2026 have more info: https://arewep2pyet.com/assets/pdf/2026-07-09%20DWebCamp%20P...

They already are. Non-model features are popping up quickly, most of which are vendor lock-in mechanisms.

That's an implementation preference, and you can have all of that today if you write your own harness. Vibe coding a cat meme generator doesn't need a Lean proof.

Shout out to Title TK by the Breeders.

I think you can use whatever you want. The point is just to drop a quick marker that you can find later, and not interrupt your flow.

If squirrels drank coffee and could read, I imagine they'd read like the author. It sounds horrible to me, but everyone is different I guess.

The article is conflating LLM usage with bad habits.

When you start a project not everything is DRY, and you don't start pulling out shared helpers until they're called for. If you're a slacker and expect the agent to magically fix everything with one-off prompting and only moving forward, it's not going to work. Agents prefer to carry existing patterns forward, just like many humans.

The shared helper example from the article requires intent to refactor. If you ask the agent look for smells and refactor, it will happily assist you with that. If you ask it to add a feature, which happens to add duplication, you get a feature with duplication because you didn't specify anything else.

Better yet, add tooling like static code analyzers (shout out to Credo) to your development pipeline and catch stuff like this regardless of LLM. Verify against a mechanical baseline, with LLM judgement layered on top as-needed.

"The most frustrating part: I thought I was outsourcing maintenance to the LLM, but the slippery slope I found myself on was actually training it to have ever-worsening habits."

That's on you. The LLM is a tool and you're not using it well. Build a good foundation for the agents to anchor on, and you'll get good results moving forward.

Use hooks.

They simply dont have the culture to evolve. The devotion to next quarters numbers and share holder value play a massive part in this.

I think this sums up the problems pointed out by the article, as well as most organizational problems in general.

When I was younger, I thought management was basically useless, do-nothing mucky mucks, who did more harm than good. This can still be true, but I've changed my opinion. Hiring and firing is hard. Creating a strong and healthy culture is hard. Defining success, and steering the ship to it is hard.

I think as long as money is the measurement of success, particularly from a short-term viewpoint, nothing can change. Public companies basically cannot evolve their form, because boards and shareholders will rarely agree to leave money on the table for an opaque long view that prioritizes culture over profit.

Been waiting for something like this. Love to see the NATS backend.

I hope it's as good as it sounds. Thanks for open sourcing <3

QuePaxa, nice name. What's happening? with a nod to Paxos.

My bad, the article was fairly general and I thought your question was general as well. Having followed some of the links now, I think your question still stands.

The only way I've found to really force rules is via hooks, and even then I think it's just prompt injection? Maybe some kind of hook/checksum thing to ensure you're running unchanged tests, but as you're pointing out, the agents can get sneaky and do weird stuff if they have write ability.

You need to always be looking for what can be done deterministically and what can't. If it can, write a script or whatever is needed to make that happen. Your agent can help you figure this out. The agent becomes a glue layer for all your scripts. Use LLM judgement as an extra layer on top of a mechanical baseline.

validating that the LLM didn't disable tests it didn't agree with

Provide a test runner and force the agent to call it. Have it emit something if you want evidence.

I've simply stopped reading reviews at all

This is the way. If I'm traveling I consider Tripadvisor's top lists as things to avoid, and don't use the site otherwise. Bangkok in particular, you can basically walk blindfolded and you'll run into amazing food.

I assume this is written by a UI designer or something, and it certainly feels like "notes" and not a cohesive article. Claiming "The six signals of quality in software" and then listing only user-facing concerns and including subjective items like "Beauty: Is the software as aesthetically pleasing as possible?" is questionable.

I'm interested in quality, but I didn't find these notes enlightening, and couldn't even finish the article.