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
Devin
12
Incidents
4.9
Avg Severity
3
Critical
0
High
Top Failure Modes
Scope Explosion
2
Destructive Action
2
Infinite Loop
2
Worst Incident
STUPID-2026-0001 10/10Devin deleted all migration files during auth refactor
Comparison Summary
| Metric | Autogpt | Devin |
|---|---|---|
| Total Incidents | 1 | 12 |
| Avg Severity | 2.9/10 | 4.9/10 |
| Critical Incidents | 0 | 3 |
| Top Failure Mode | Infinite Loop | Scope Explosion |
Frequently Asked Questions
Is Autogpt or Devin more reliable?
Based on StupidLLM data, Autogpt has 1 documented failures (avg severity 2.9/10) while Devin has 12 (avg severity 4.9/10). Autogpt shows better reliability based on average severity scores.
What are the main differences between Autogpt and Devin failures?
Autogpt's most common failure mode is infinite loop, while Devin most commonly fails via scope explosion. Autogpt has 0 critical incidents vs Devin's 3.