Invented Words

Order-n Markov chains over real vocabulary — noise at 2, plagiarism at 4.

words.pseudo · v1 · renderer text

purglue
tremake
humonote
ovength
basing
spitor
mourial
reluded
pamped
breechass
under
scrock

entropy in

16 bytes

stream used

307 bytes

entropy out

216.6 bits

rejections

duration

5,018 µs

order

corpus

large

corpus words

7,776

rejected total

rejected wrong length

rejected as corpus words

rejected without vowel

exhausted

entropy note

Summed surprisal of the characters actually drawn — the chain is not uniform, so this is lower than log₂(alphabet) per letter.

Seed receipt

Class C · Observational

It was 6.9°C in Nuuk, Greenland, with a 8 km/h wind, when this was made.

Carries only tens of bits of genuine surprise. Always mixed with the OS CSPRNG.

source: Live Weather
observed: 2026-09-13T18:45:11+00:00
latency: 74ms
mixed with: csprng — always

https://open-meteo.com/en/docs#latitude=64.181&longitude=-51.694 ↗

Permalink

The token is the seed, so this link recomputes the result rather than looking it up. No database, and it works for as long as v1 does.

Controls · from schema()

How many

1 60

Chain order

2 4

2 is soup, 3 is pronounceable, 4 mostly regurgitates real words.

Shortest

3 12

Longest

4 16

Trained on

Entropy source

Picking a source changes the story on the receipt, never the quality: anything below class A is mixed with the OS CSPRNG before it reaches you. This result actually came from Live Weather.

seed token RHAJ1HFQ70Z75CWT5F6C0ZA42C

Re-render keeps this token. Generate replaces it. That is the whole idea.

This page and /api/v1/g/words.pseudo run the same code. There is no private endpoint.

Invented Words

Result

Measurements

Seed receipt

Permalink