Concept detail
self-preferential bias in LLM judges
0 tagged videos · 1 connection videos · degree 0
Publication timeline
- 2026-101 video
Source videos
Observed neighbors
fresh prover / blind judge verification
Treats evaluation independence as an architectural requirement rather than a prompt-level instruction.
1 source videos
Why One AI Agent Isn’t Enough (And How to Run 1,000) - CJ Avilla & Harrison Stall, AnthropicRelated tagged insights
No core insights are tagged with this concept.