collinear-ai/yc-bench
1
0
Fork 0
mirror of https://github.com/collinear-ai/yc-bench.git synced 2026-04-19 12:58:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Rename Greedy Bot to Human Devised Rule in README

Browse source 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
adit jain 2026-02-27 16:21:32 -08:00
parent 763ed3d750
commit 6d6f0a855d
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -417,7 +417,7 @@ The hardened default is designed so that the obvious strategies fail:
Each radar shows final prestige across 7 domains (1 = center, 10 = edge). Large polygons = the model climbed prestige broadly. Tiny dots near center = bankrupt before gaining any prestige. Pointy shapes = domain specialization.
**Greedy Bot** (navy dashed) consistently fills the full radar — it mechanically maxes prestige everywhere. Among LLMs, **Gemini** builds the most balanced prestige profiles. **GPT-5.2** shows clear specialization on medium (backend/data/frontend high, training untouched). **Sonnet** is bimodal: either maxes everything (medium seed 1) or collapses entirely (nightmare seeds 1 & 3).
**Human Devised Rule** (navy dashed) consistently fills the full radar — it methodically maxes prestige everywhere. Among LLMs, **Gemini** builds the most balanced prestige profiles. **GPT-5.2** shows clear specialization on medium (backend/data/frontend high, training untouched). **Sonnet** is bimodal: either maxes everything (medium seed 1) or collapses entirely (nightmare seeds 1 & 3).
### Why models fail