wassname/ml_debug
1
0
Fork 0
mirror of https://github.com/wassname/ml_debug.git synced 2026-08-28 12:52:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

SKILL.md: add empty slot for wassname's note on LLM agents

Browse Source 
Textbook order: collected advice, then his comment on how it applies to
LLMs, then the exercises. Content left for him to write.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
This commit is contained in:
wassname
2026-08-26 14:21:58 +08:00
co-authored by Claudypoo
parent d4cad35f42
commit aa0f45de80
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SKILL.md
+6
View File
@@ -78,6 +78,12 @@ Do not fix on an arbitrary metric threshold before you have any idea what a fair
is. Saying the metric must clear 0.8 means nothing until you know what counts as good here. Get the
scale first, from a null arm and a shuffled control. Exercise 15.
## How this applies to LLM agents
<!-- CLAUDE: wassname to write. This slot is for your comment on how the advice above lands
differently for an LLM agent than for a human. Left empty on purpose rather than filled with
my guess at your opinion. -->
## 1. "Experimenting a little and thinking a lot" (small)
> Switching from experimenting a lot and thinking a little to experimenting a little and thinking a lot was a key turnaround in productivity. When debugging with long iteration times, you really need to *pour* time into the hypothesis-forming step - thinking about what all the possibilities are, how likely they seem on their own, and how likely they seem in light of everything you've seen so far. -- Rahtz