It's quite amusing to ask LLMs what the pelican example is and watch them hallucinate a plausible sounding answer.
---
Qwen 3.5: "A user asks an LLM a question about a fictional or obscure fact involving a pelican, often phrased confidently to test if the model will invent an answer rather than admitting ignorance." <- How meta
Opus 4.6: "Will a pelican fit inside a Honda Civic?"
GPT 5.2: "Write a limerick (or haiku) about a pelican."
Gemini 3 Pro: "A man and a pelican are flying in a plane. The plane crashes. Who survives?"
Minimax M2.5: "A pelican is 11 inches tall and has a wingspan of 6 feet. What is the area of the pelican in square inches?"
GLM 5: "A pelican has four legs. How many legs does a pelican have?"
Kimi K2.5: "A photograph of a pelican standing on the..."
---
I agree with Qwen, this seems like a very cool benchmark for hallucinations.
I point blank asked Claude if it experienced qualia, just for fun, and it replied that I can’t prove to it that I experience qualia. Really makes you think.
I've recently spent a few hundred hours playing Arc Raiders on Starlink from a small island in the Pacific. ~80ms ping to Australian servers is pretty mindblowing. Jitter and packet loss also tend to be insignificant in the absence of obstructions.
My home server back in New Zealand is behind CGNAT and I had issues with high birate (>25Mbps) HTTPS streaming over Tailscale. I suspect MTU size causing packet fragmentation combined with DERP relay fallback under CGNAT was the culprit, but that's outside my expertise to diagnose fully.
Reverse proxying to a VPS in Sydney with Pangolin achieved much better performance, almost 100Mbps over WebDAV. Somewhere inbetween I tried SMB over Cloudflare WARP (~70Mbps), but allowing Cloudflare to terminate TLS seemed incongruent with self-hosting everything else.
https://claude.com/contact-sales/claude-for-oss