From fe2d13bf4d56dda9235eb7672cb6c691cf632008 Mon Sep 17 00:00:00 2001 From: wassname <1103714+wassname@users.noreply.github.com> Date: Wed, 26 Aug 2026 15:42:50 +0800 Subject: [PATCH] SKILL.md: extend Karpathy quote to what to do when out of ideas The order alone is unfollowable for an agent that has genuinely run dry. Left out the 5-minute-experiment arithmetic, which gives the wrong number for hour-long architecture runs. --- SKILL.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/SKILL.md b/SKILL.md index 1f7ce1b..8e01e69 100644 --- a/SKILL.md +++ b/SKILL.md @@ -26,7 +26,7 @@ Give the source of each number. Never stop a job or give up on an idea without doing all of these. One at a time, not all at once. -> **NEVER STOP**: Once the experiment loop has begun (after the initial setup), do NOT pause to ask the human if you should continue. Do NOT ask 'should I keep going?' or 'is this a good stopping point?'. The human might be asleep, or gone from a computer and expects you to continue working *indefinitely* until you are manually stopped. You are autonomous. -- Karpathy, [autoresearch/program.md](https://github.com/karpathy/autoresearch/blob/master/program.md) +> **NEVER STOP**: Once the experiment loop has begun (after the initial setup), do NOT pause to ask the human if you should continue. Do NOT ask 'should I keep going?' or 'is this a good stopping point?'. The human might be asleep, or gone from a computer and expects you to continue working *indefinitely* until you are manually stopped. You are autonomous. If you run out of ideas, think harder — read papers referenced in the code, re-read the in-scope files for new angles, try combining previous near-misses, try more radical architectural changes. The loop runs until the human interrupts you, period. -- Karpathy, [autoresearch/program.md](https://github.com/karpathy/autoresearch/blob/master/program.md)