Is Multiple LLMs reliable?

Based on 3 documented incidents, Multiple LLMs has an average failure severity of 3.8/10. 0 incidents were rated critical and 0 were rated high severity.

What are the most common Multiple LLMs failures?

The most common failure mode is hallucination. Multiple LLMs has 0 critical incidents.

How many Multiple LLMs AI failures have been documented?

StupidLLM has documented 3 Multiple LLMs AI agent failures. Each incident is severity-scored on a 0-10 scale and verified against source evidence.

Agent report

Multiple LLMs failures

3 documented incidents, average severity 3.8/10. Most common failure mode: hallucination.

n = 3

Not a single vendor

These reports describe multi-agent or unattributed failures and are never counted toward any individual vendor.

Incidents

3.8

Avg severity

Critical

Verified

Severity breakdown

Stacked severity breakdown per agent. Longer bar = more incidents.

Failure modes

Distribution of failure modes across all documented incidents.

Worst documented incident

6.4

medium

Slopsquatting: LLMs hallucinate package names attackers pre-register (react-codeshift, unused-imports)

All 3 incidents

STUPID-2026-0033

6.4

Slopsquatting: LLMs hallucinate package names attackers pre-register (react-codeshift, unused-imports)STUPID-2026-0049

2.5

AI 'CVE slop' is drowning open-source maintainers: 60-80% of HackerOne submissions now invalid STUPID-2026-0037

2.5

AI 'slop' vulnerability reports flooded curl until it killed its bug bounty