Multiple Llms
3
Incidents
3.8
Avg Severity
0
Critical
0
High
Top Failure Modes
Hallucination
3
Worst Incident
STUPID-2026-0033 6.4/10Slopsquatting: LLMs hallucinate package names attackers pre-register (react-codeshift, unused-imports)
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 | Multiple Llms | Unknown Agent |
|---|---|---|
| Total Incidents | 3 | 4 |
| Avg Severity | 3.8/10 | 8.5/10 |
| Critical Incidents | 0 | 3 |
| Top Failure Mode | Hallucination | Security Vulnerability |
Frequently Asked Questions
Is Multiple Llms or Unknown Agent more reliable?
Based on StupidLLM data, Multiple Llms has 3 documented failures (avg severity 3.8/10) while Unknown Agent has 4 (avg severity 8.5/10). Multiple Llms shows better reliability based on average severity scores.
What are the main differences between Multiple Llms and Unknown Agent failures?
Multiple Llms's most common failure mode is hallucination, while Unknown Agent most commonly fails via security vulnerability. Multiple Llms has 0 critical incidents vs Unknown Agent's 3.