Mossly

You can also use @AGENTS.md which automatically concatenates the files

This inspired me to check lol. Brysbaert et al. (2019) collected word prevalence norms (the share of people who report knowing each word) for ~62K English lemmas from ~220K participants.

fable: 99/100 sonnet: 97/100 haiku: 91/100 opus: 89/100

So while these terms are almost universally known, opus is indeed the least known of the four. And I guess this only measures whether a person knows a word, not whether they know an opus is longer than a sonnet! Personally I only inferred that based on the related term 'magnum opus.'

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.

Seeing auth succeed but push fail was an exercise in hair pulling.

I've found Gitea to be pretty rock solid, at least for a small team.

I did this recently with my unsorted bookmarks! It was the first time I used parallel API calls. Ten gpt-4-nano threads classifying batches of ten bookmarks ripped through 10,000 bookmarks in a few minutes.

Very neat, this kind of classification & sentiment analysis with flavour text is a use case where LLMs really shine.

For whatever reason, I'm getting an error in the Server Components render when trying my username. My first thought was that it might be due to having no submissions, just comments — but other users with no submissions appear to work just fine.

Anybody wanting more should check out “The Flute and Flute Playing” (1871) by Theobald Boehm - an autodidact polymath who employed his talents in metalworking and physics to iteratively perfect the metal cylinder bored flute.

It contains detailed explanations of his development process, including a complete schema for determining optimal tonehole positions - developed after he first created a flute in which he could move them!

It helped me to more deeply appreciate the engineering marvel that is the modern western concert ‘Boehm’ flute. It’s an exceptionally pure instrument.

0.5 arcminutes really puts this into perspective — for reference the orion nebula spans about 1 degree