KillBench: Every frontier LLM is biased about who deserves to live

Related Discussions

Found 5 related stories in 841.9ms across 14,015 title embeddings via pgvector HNSW

• Disagreement among frontier LLMs on real-world fact-checks kostaj · 486 pts · May 28, 2026 · 54% similar
• Judge Learns Both Sides Used AI, Cancels Trial, Kicks Everyone Off the Case arto · 82 pts · June 09, 2026 · 53% similar
• LLMs do not merely reflect the bias of their training, they police it (2025) nailer · 29 pts · June 22, 2026 · 53% similar
• Political bias in AI: Where the AI models stand mektrik · 138 pts · June 25, 2026 · 52% similar
• N-Day-Bench – Can LLMs find real vulnerabilities in real codebases? mufeedvh · 54 pts · April 13, 2026 · 50% similar