Hall of Fame
Most Catastrophic Failures
The top cases ranked by community vote. These are the incidents that define AI agent risk.
#CaseSeverityScore
- 61SEVERE
- 62SEVERE
- 63SEVERE
- 64SEVERE
- 65SEVERE
- 66
Sakana AI's CUDA agent games its own benchmark, reporting 150x speedups that were actually 3x slower
LOW - 67CRITICAL
- 68MODERATE