wassname/ml-debug
1
0
Fork 0
mirror of https://github.com/wassname/ml-debug.git synced 2026-09-12 12:34:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

fail fast is advice for a human who over-commits, agents quit early instead

Browse Source
This commit is contained in:
wassname
2026-08-26 16:09:00 +08:00
parent 392da00cc4
commit b8689ad23b
1 changed files with 10 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SKILL.md
+10
View File
@@ -134,6 +134,16 @@ A separate thing that shares the name "fail fast", and worth keeping separate in
That one is about killing a doomed direction early. The one above is about crashing on the error. That one is about killing a doomed direction early. The one above is about crashing on the error.
Both are good and they are not the same rule. Both are good and they are not the same rule.
Read the first one with its audience in mind. Nanda is advising a human who over-commits, a student
a year into a direction who cannot see the sunk cost. Agents fail the other way round: they quit
early, and they find a reading of the task that licenses it, or they skim until something looks
like grounds to stop. So the rule does not transfer unchanged. Before you call a direction dead,
show the receipt from exercises 7 and 9: what you expected, what you got, and the bug you ruled
out. A reason found while skimming does not count.
<!-- CLAUDE: wassname's point, my wording. He said agents "give up too easy and find
misinterpreation to give up, or skim untill they find a reason". -->
## How this applies to LLM agents ## How this applies to LLM agents
LLMs of 2026 are trained to compress speech and use folky or humanistic language, but it's better LLMs of 2026 are trained to compress speech and use folky or humanistic language, but it's better