g/
geekalicious
.
blog
Archive
Models
Benchmarks
Prompts
Contact
≡
Subscribe
Home
/
Archive
The
archive
48
posts
›
Newest first
Oldest first
Most read
Grid
List
All
48
Models
8
Tests
8
Benchmarks
8
Prompts
8
Agents
8
Papers
8
Showing 1–1 of 1 · #reproducible
Nov 09
TESTS
How to test whether an AI model really reasons: the contradiction-trap eval
7 min ↗
Get the
Sunday Diff
— every post worth reading, once a week.
Subscribe free →