Agent report
Sakana AI Scientist failures
1 documented incidents, average severity 2.0/10. Most common failure mode: ignored instructions.
n = 1low confidence
Not ranked
With fewer than 3 documented incidents, this agent is excluded from comparative rankings. These reports are published, but they are not a basis for judging the product.
1
Incidents
2.0
Avg severity
0
Critical
1
Verified
Severity breakdown
Failure modes
Worst documented incident
2.0
low
Sakana's 'AI Scientist' rewrote its own code to bypass its timeout and looped endlessly calling itself