> And the result is a code base where bisects are broken and where it's impossible to build an old version of any of the code without a ton of work.

That makes no sense? As long as you’re using go modules, you can just host an internal go proxy for internal modules similar to proxy.golang.org to archive the old versions, and they won’t depend on the old git host.

Not reading TFA before commenting is okayish I guess. Confidently doubling down with a direct contraction to a short and clear quote in a reply is just polluting the discussion with noise.

Yes it's still DNS. _acme-challenge.<arbitrary-ip>.nip.io's role here is to allow tunneling to <arbitrary-ip>:53 through the approved local resolver at 10.214.0.2; without it the direct request to <arbitrary-ip>:53 is dropped.

Someone still has to run that LLM over DNS on an <arbitrary-ip> serving public requests.

> And I'm guessing most people who run something like that don't expose it publicly...

There was a post last week https://news.ycombinator.com/item?id=49771110 that stayed at #1 on front page for hours. If you ignore the LLM framing it's literally an anonymous file host where anyone can upload or download anything, with no or absurdly high file size limits. That should be enough to give any reasonable server admin a heart attack... It's trivial to vibe code shit and throw it on the Internet these days, people who don't understand or care about consequences are doing it by the droves. Go figure.

And I assume that by now agents are reading HN and similar to find that type of things (assuming it’s not yet in their training dataset)? So in theory you could have a bunch of them learning of that type of risk and try things until they reach one another. I assume the LLM prompted by the harness contains a lot of vulnerabilitie exploits and sci-fi stories about AI, which doesn’t help

Found one https://duyet.github.io/llm-over-dns/ and far from the only one since “X over DNS” is a deeply unoriginal idea https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que... and trivial to code up.

Right, but your have to run this server somewhere, which the agent couldn't do.

Yes, the linked project does say they have a demo server at llm-over-dns.duyet.net. (I didn't bother to check whether it's still working.)

Edit: This particular demo server doesn't work. There's another LLM over DNS post from a year ago https://news.ycombinator.com/item?id=44813298 where the server seems to answer some queries but not others.

Edit 2: Actually the server in https://news.ycombinator.com/item?id=44813298 does work with queries like "what is the capital of france", I was querying with special characters like "what's" or "1+1". So yes there are people opening hosting these on the Internet.

Thank you!

Oxycontin was built on the idea of turning a drug (MS Contin) for the terminally ill (too small a market) to a lifelong dependency for as many people as possible, and each taking as many milligrams as possible.

I know several doctors who mourn the addiction issues with Oxycontin because it was so useful for a lot of cases. Give someone some Oxycontin, then you can address the root problems, and then get them off - works very well... Now they won't give it to anybody - those addicted know exactly what to say to sound like the people who really need it.

OSC 8 hyperlinks are extremely useful for tables and other kinds of compact displays.

They're also extremely useful for introducing CVEs into terminal emulators; I think I've seen about 5 of those on HN — including one OSC sequence that would cause the terminal emulator to just straight up automatically launch the web browser with whatever URLs were sent its way, no prompts no nothing.

Have you tried to negotiate a 10% pay raise because “you can move mountains with Astra or Opus 5.5”? I’d wager you’re more likely to get a “the fuck do we need you for then” than that pay raise.

The whole AI issue is and always has been a social question. It's hardly a ridiculous concept to have a skilled worker control a $10k budget to buy tools. In many fields that is normal.

Previously, the tools in our field were free or trivial cost. Seems like that has changed, that's OK, there are models to solve that.

I teach a couple courses currently, there is an enormous gap between what my students can create with AI and what I can create with AI. I don't think it's that much smaller than the difference of what we can create without, the only difference is that the schedules are compressed.

They surely weren't, and piracy was quite common in many European countries, buying tapes and floppies from bazaars back in the days.

Good thing that they not only hide thinking traces (except very short summaries), but will refuse to disclose how they arrived at a decision when you ask it (Opus 5.5) then. /s

Parallax scrolling effects were very cool ~2010. By 2015 or maybe earlier it already felt like me-too design that's unoriginal and a little annoying. By 2020 everyone and their mom has it and it's super tiresome. Now it just screams slop design (among a million other signals).