hyperknot

There was no cache write before!

https://openrouter.ai/openai/gpt-5.5?endpoint=58e5b336-423e-...

vs

https://openrouter.ai/openai/gpt-5.6-sol?endpoint=a54c5de0-8...

> GPT‑5.6 also introduces more predictable prompt caching, including support for explicit cache breakpoints (opens in a new window) and a 30-minute minimum cache life.

Great to read they are moving away from the 5 minute cache defaults. Hopefully other providers follow soon!

Add this to fix the contrast in all your dark themes:

  "experimental.theme_overrides": {
    "background": "#111",
    "panel.background": "#111",
    "text": "#eee",
    "text.muted": "#ccc",
    "title_bar.background": "#111",
    "tab_bar.background": "#111",
    "toolbar.background": "#111",
    "status_bar.background": "#111",
    "element.selected": "#333",
    "editor.background": "#000",
    "editor.gutter.background": "#000"
  }

Use a simple block rule, not a WAF rule, those are free.

Yes, wplace could solve their whole need by a single, custom-built static pmtile. No need to serve 150 GB of OSM data for their use-case.

You are correct. I was putting "a caching server on their side" in the context of their side being a single dev hobby project running on a VPS, exploding on the weekend. I agree that these servers do exist and some companies do pay for this bandwidth as part of their normal operations.

I'm sure the server hardware is not a problem. The full dataset is 150 GB and the server has 64 GB RAM, most of which will be never requested. So I'm sure that the used tiles would actually get served from OS cache. If not, it's on a RAID 0 NVME SSD, connected locally.

What I've been referring to is the fact that even unlimited 1 Gbps connections can be quite expensive, now try to find a 2x40 gig connection for a reasonable money. That one user generated 200 TB in 24 hours! I have no idea about bandwidth pricing, but I bet it ain't cheap to serve that.

OK, technically there might exist such server, I guess Netflix and friends are using those. But we are talking about a community supported, free service here. Hetzner servers are my only options, because of their unmetered bandwidth.

They are actually static files. There is just too many of them, about 300 million. You cannot put that in Pages.

Yes, that's a good idea. But we are talking about 90+% of the titles being empty (I might be wrong on that), that's a lot of hard links. I think the nginx config just need to be fixed, I hope I'll receive some help on their forum.

I've just written my question to the nginx community forum, after a lengthy debugging session with multiple LLMs. Right now, I believe it was the combination of multi_accept + open_file_cache > worker_rlimit_nofile.

https://community.nginx.org/t/too-many-open-files-at-1000-re...

Also, the servers were doing 200 Mbps, so I couldn't have kept up _much_ longer, no matter the limits.

We are talking about an insane amount of data here. It was 56 Gbit/s (or 56 x 1 Gbit servers 100% saturated!). This is not something a "caching server" could handle. We are talking on the order of CDN networks, like Cloudflare, to be able to handle this.

Yes, I designed the whole path structure / location blocks with caching in mind. Here is the generated nginx.conf, if you are interested:

https://github.com/hyperknot/openfreemap/blob/main/docs/asse...

What if one user really wants to browse around the world and explore the map. I remember spending half an hour in Google Earth desktop, just exploring around interesting places.

I think referer based limits are better, this way I can ask high users to please choose self-hosting instead of the public instance.

Feel free to migrate. If you ever worry about High Availability, self-hosting is always an option. But I'm working hard on making the public instance as reliable as possible.

I got 700+ tokens/sec on o3 after the announcement, I suspect it's very much a quantized version.

https://x.com/hyperknot/status/1932476190608036243

Update: news sites have pulled the video now, confirming parts of it were AI generated.

https://deadline.com/2025/05/nbc-viral-chinese-paraglider-vi...

This is actually correct, I don't know why is it downvoted. All current models have their identity "burned-in", not needing system prompt for that.

Thanks! My idea was to just render a Lorem Ipsum paragraph and compare the calculated width-height across a know list of default fonts. Of course it wouldn't work with fixed width fonts, for that I'd need a canvas bitmap comparison.

Nice project! Related question, how would you recommend detecting which font is being used for names like ui-sans-serif, system-ui on a given device/browser?

I guess the benefit would be possibly higher SEO / DR, as you'd have a lot of backlinks scattered around the interwebs. But then it can be misused and then all your domain can also be trashed.

I believe this is probably beneficial for bigger companies / VC funded projects where they have the resources for moderation.

I'm thinking of launching a new app where a single click share would be a feature worth implementing, but definitely not part of the core functionality. I'm trying to figure out if this feature is worth implementing at all, or it's just asking for trouble.

Luckily I'm still at the planning stage, no UGC problem yet. I'm thinking of launching a new app where a single click share would be a feature worth implementing, but definitely not part of the core functionality. I'm trying to figure out if this feature is worth implementing at all, or it's just asking for trouble.

Absolutely! It's actually shown by default, OP shouldn't be turning it off.

Also, if you run out of free Mapbox credits, feel free to change the basemap to openfreemap.org (I'm the creator).