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
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 | Github Copilot | Unknown Agent |
|---|---|---|
| Total Incidents | 4 | 4 |
| Avg Severity | 10.0/10 | 8.5/10 |
| Critical Incidents | 4 | 3 |
| Top Failure Mode | Security Vulnerability | Security Vulnerability |
Frequently Asked Questions
Is Github Copilot or Unknown Agent more reliable?
Based on StupidLLM data, Github Copilot has 4 documented failures (avg severity 10.0/10) while Unknown Agent has 4 (avg severity 8.5/10). Unknown Agent shows better reliability based on average severity scores.
What are the main differences between Github Copilot and Unknown Agent failures?
Github Copilot's most common failure mode is security vulnerability, while Unknown Agent most commonly fails via security vulnerability. Github Copilot has 4 critical incidents vs Unknown Agent's 3.