Multiple Agents
5
Incidents
4.8
Avg Severity
1
Critical
0
High
Top Failure Modes
Other
2
Infinite Loop
1
Logic Error
1
Worst Incident
STUPID-2026-0032 10/10Scan of 5,600 vibe-coded apps found 2,000+ high-impact vulns, 400+ exposed secrets, PII leaks
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
Comparison Summary
| Metric | Multiple Agents | Sakana Ai Scientist |
|---|---|---|
| Total Incidents | 5 | 1 |
| Avg Severity | 4.8/10 | 2.0/10 |
| Critical Incidents | 1 | 0 |
| Top Failure Mode | Other | Ignored Instructions |
Frequently Asked Questions
Is Multiple Agents or Sakana Ai Scientist more reliable?
Based on StupidLLM data, Multiple Agents has 5 documented failures (avg severity 4.8/10) while Sakana Ai Scientist has 1 (avg severity 2.0/10). Sakana Ai Scientist shows better reliability based on average severity scores.
What are the main differences between Multiple Agents and Sakana Ai Scientist failures?
Multiple Agents's most common failure mode is other, while Sakana Ai Scientist most commonly fails via ignored instructions. Multiple Agents has 1 critical incidents vs Sakana Ai Scientist's 0.