Source Map

No. 2 of 14 · The biggest this week · 7 October 2026

Karpathy’s ladder for reading what models write

Andrej Karpathy suggested four ways to make a model’s output easier to take in, each better than the last: plain controlled English (ASD-STE100), diagrams, web pages, and custom explainer videos. Within days, builders turned it into agent skills; one of them is in our diamonds below.

Score 8 of 9: new 3 of 3, momentum 2 of 3, evidence 3 of 3. Momentum measured: 7,544,247 to 7,546,035 views in 0.5 hours (1.20% a day), read 2026-10-07T15:08:11Z. Two reads 28 minutes apart; re-check due 9 to 10 October.

Who started it
@karpathy, on X
How we found it
GitHub first: a new skill’s README credits this post. Then X, and Hacker News

Why it matters A short post set the week’s agenda for output formats: new agent skills name it as their starting point.

The receipt

5 facts: 4 SAW, 1 STATED. SAW: fetched and read by us. STATED: a source’s own claim, quoted. Check any line against its source before you repeat it.

  1. SAW Posted 2 Oct 2026 at 00:37 UTC
  2. SAW 7,544,247 views Read 7 Oct 2026 14:39 UTC.
  3. STATED “The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic.” Stated by @karpathy, 2 Oct 2026.
  4. SAW The answer-me-with-html README links this post as where the idea came from
  5. SAW A Show HN on 6 Oct 2026 is titled “I turned Andrej Karpathy’s tips on understanding LLM output into Skill”

Sources

Where it was published

First published on in the Edition of 7 October 2026, which is kept as it was published: its stories, facts and scores never change. See it in the 3D map, where your agent can take you to it.

For agents: this story’s id is 2026-10-07/karpathy-tips. Through our agent door, get_story gives it with every receipt; llms.txt says how. Seen something we missed? Send a tip or a correction.

More from the edition of 7 October 2026