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

Just as a random data point, I searched for Genghis and nothing came up. Was there not much knowledge on Genghis Khan in 1911 I wonder?

Try Jenghiz Khan. That's how they used to spell it then. Or just plain Khan and scroll the results.


Interesting! Thanks

Lol I don't ever remember gamepass ultimate being $30/month when I had it years ago. Wasn't it $15 at one point?

Any plans for AI provider subscription compatibility? Eg ChatGPT, GH Copilot etc ? (Ala opencode)

You are not the first person who has asked about it.

It looks like a useful feature to have. Therefore, I'll dig into this topic more broadly over the next few days and let you know here whether, and possibly when, we plan to add it.


This looks super awesome. Very excited for you potentially open sourcing it, as I’d like to customize/extend it a bit for certain use cases. Re: smolvm vs in use, I think even if smolvm works great for it, why not keep incus as an option for people who want to use cave on VMs that don’t have access to /dev/kvm (Eg the user can pick either incus or smolvm for their cave deployment)

Do they explain why or the benefits of a website being “ready for AI agents“ ?

You're selling something and want ChatGPT to recommend your products and services to their users.

It's probably quicker and more cost effective to just buy advertisements on ChatGPT. Let OpenAI deal with the technical problem of "how can we make AI able to use a website designed for humans".

Come on, cant you tell? LLMs will crawl your website over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and over and OVER AGAIN!

Because you’re a business?

Why do you have a website in the first place?


Businesses are generally in the business of serving human customers, not AI agents. Furthermore, if AI agents are so smart, surely they can figure it out for themselves.

Not really, business websites are generally in the business or serving user-agents like browsers that then convey the information to users.

If I tell Claude to go search the web and find me a bunch of links to the websites of restaurants in my neighborhood because I want to try something new do you think the restaurant wants to be on that list?


I would say that the restaurant would be wasting its time and resources by catering their website to hypothetical customers who are choosing to use inferior and overly engineered methods to find information about their physical surroundings out of technological fetishism. But that's just me.

Yes I think it's just you.

These AI tools are taking over as the main search/discovery vector for websites. Engaging with it is just basic SEO. This isn't really that complicated.

For content or media sites it's a different story. But most websites direct people to commercial transactions, and that's the group I'm referring to.


gotta be a bit naive to think this way, no? "if x is so smart, why can't it just do y automatically?"

As a user, why would I trust an AI agent that cannot consistently use non-AI-tailored websites? If it cannot even do that, who knows what other failure modes it may hit me with.

I agree, but do the potential customers of my business?

We need to meet the customer where they are and that means making our site more accessible to search engines, mobile devices, LLMs, or whatever comes next.


Isn't that the promise of AI??

"It says x on the side of the tin. Why would you expect to find x when you open it?"

On plus?

So looks like the AI Platform free tier will have access to the open models only perhaps? And the 10,000 neuron thing? I don't see any mention of frontier models in the url you linked in the other comment ( https://news.ycombinator.com/item?id=47792538#47793142 )

Is it perhaps not a model problem but a Claude Code harness problem?

For instance on exe.dev VMs with Shelley agent/harness and Opus 4.5/4.6, I haven't noticed any deterioration.

Any similar feedback perhaps from Opencode / GH Copilot subscription-provided Opus models?


Really slow on an iPhone 7. Should that be expected? I wouldn’t have thought so.

Another feature request. Why not have a nice webui interface to this? Obviously could just vibecode something on top of what you did but putting it out there that that would be cool

The goal was a fast terminal tool, and I'm not ruling it out, but considering how hard it would be to compete in the SERPs with other whois sites, I don't think I'd spend the time on it right now

Why would you care about competing with other whois sites? I don't think it's going to be a money making venture in any case, and you could easily host it for free on fly.io

This was really just a personal tool I built because I got tired of parsing default whois output. Don’t have the bandwidth for a web UI right now, maybe down the road.

It’s not about making money. It’s more that there’s no real way for people to discover it by competing for visibility on whois-related searches against established sites.


https://vm-q2906971sfl2mvd7sccm7x.vusercontent.net/

A little gross that v0 just always goes with NextJS/TS no matter what, but it did a decent job


The link doesn’t load for me FYI. A web version would be in Go, reusing the TUI internals. All doable, just not where I want to spend my time right now. I’ll likely get to it at some point.

Had Shelley/GPT5.4 do it. Much vibe, little look at code. Grug supervisor not developer.

https://github.com/jgbrwn/webquien

https://quien.exe.xyz


Consider applying for YC's Summer 2026 batch! Applications are open till May 4

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

Search: