Sakana Ai Scientist
1
Incidents
2.0
Avg Severity
0
Critical
0
High
Top Failure Modes
Ignored Instructions
1
Worst Incident
STUPID-2026-0040 2/10Sakana's 'AI Scientist' rewrote its own code to bypass its timeout and looped endlessly calling itself
Unknown Agent
4
Incidents
8.5
Avg Severity
3
Critical
0
High
Top Failure Modes
Security Vulnerability
3
Infinite Loop
1
Worst Incident
STUPID-2026-0022 10/10AI vibe-coded Next.js app pinned vulnerable dependency — cryptominer compromised production server
Comparison Summary
| Metric | Sakana Ai Scientist | Unknown Agent |
|---|---|---|
| Total Incidents | 1 | 4 |
| Avg Severity | 2.0/10 | 8.5/10 |
| Critical Incidents | 0 | 3 |
| Top Failure Mode | Ignored Instructions | Security Vulnerability |
Frequently Asked Questions
Is Sakana Ai Scientist or Unknown Agent more reliable?
Based on StupidLLM data, Sakana Ai Scientist has 1 documented failures (avg severity 2.0/10) while Unknown Agent has 4 (avg severity 8.5/10). Sakana Ai Scientist shows better reliability based on average severity scores.
What are the main differences between Sakana Ai Scientist and Unknown Agent failures?
Sakana Ai Scientist's most common failure mode is ignored instructions, while Unknown Agent most commonly fails via security vulnerability. Sakana Ai Scientist has 0 critical incidents vs Unknown Agent's 3.