Claude Code
8
Incidents
6.4
Avg Severity
3
Critical
2
High
Top Failure Modes
Destructive Action
3
Other
2
Security Vulnerability
2
Worst Incident
STUPID-2026-0003 10/10Claude Code ran rm -rf on test fixtures thinking they were temp files
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 | Claude Code | Unknown Agent |
|---|---|---|
| Total Incidents | 8 | 4 |
| Avg Severity | 6.4/10 | 8.5/10 |
| Critical Incidents | 3 | 3 |
| Top Failure Mode | Destructive Action | Security Vulnerability |
Frequently Asked Questions
Is Claude Code or Unknown Agent more reliable?
Based on StupidLLM data, Claude Code has 8 documented failures (avg severity 6.4/10) while Unknown Agent has 4 (avg severity 8.5/10). Claude Code shows better reliability based on average severity scores.
What are the main differences between Claude Code and Unknown Agent failures?
Claude Code's most common failure mode is destructive action, while Unknown Agent most commonly fails via security vulnerability. Claude Code has 3 critical incidents vs Unknown Agent's 3.