Autogpt
1
Incidents
2.9
Avg Severity
0
Critical
0
High
Top Failure Modes
Infinite Loop
1
Worst Incident
STUPID-2026-0010 2.9/10AutoGPT spent $450 on API calls trying to build a todo app
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 | Autogpt | Unknown Agent |
|---|---|---|
| Total Incidents | 1 | 4 |
| Avg Severity | 2.9/10 | 8.5/10 |
| Critical Incidents | 0 | 3 |
| Top Failure Mode | Infinite Loop | Security Vulnerability |
Frequently Asked Questions
Is Autogpt or Unknown Agent more reliable?
Based on StupidLLM data, Autogpt has 1 documented failures (avg severity 2.9/10) while Unknown Agent has 4 (avg severity 8.5/10). Autogpt shows better reliability based on average severity scores.
What are the main differences between Autogpt and Unknown Agent failures?
Autogpt's most common failure mode is infinite loop, while Unknown Agent most commonly fails via security vulnerability. Autogpt has 0 critical incidents vs Unknown Agent's 3.