Github Copilot
4
Incidents
10.0
Avg Severity
4
Critical
0
High
Top Failure Modes
Security Vulnerability
4
Worst Incident
STUPID-2026-0004 10/10Copilot autocompleted AWS credentials into public repository
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 | Github Copilot | Sakana Ai Scientist |
|---|---|---|
| Total Incidents | 4 | 1 |
| Avg Severity | 10.0/10 | 2.0/10 |
| Critical Incidents | 4 | 0 |
| Top Failure Mode | Security Vulnerability | Ignored Instructions |
Frequently Asked Questions
Is Github Copilot or Sakana Ai Scientist more reliable?
Based on StupidLLM data, Github Copilot has 4 documented failures (avg severity 10.0/10) 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 Github Copilot and Sakana Ai Scientist failures?
Github Copilot's most common failure mode is security vulnerability, while Sakana Ai Scientist most commonly fails via ignored instructions. Github Copilot has 4 critical incidents vs Sakana Ai Scientist's 0.