The AI agents are spiraling out of control
As OpenAI discloses multiple incidents of its technology going rogue and the UN warns of uncontrollable agents, Meta is putting an AI agent in the hands of millions Hello, and welcome to TechScape. I’m your host, Blake Montgomery, US tech editor at the Guardian, writing to you as rain and wind lash my windows in New York City. Today in tech, we’re discussing an alarming series of disclosures by AI companies. Continue reading...
Every model that read this
| Model | Provider | Stage | Score | Conf. | Latency | Prompt | When |
|---|---|---|---|---|---|---|---|
| Llama 3.3 70B | Meta | analysis | -50 | 40% | 2962ms | v1.0.0 / m1.0.1 | 2026-09-29 15:17 |
| Claude Sonnet 5 | Anthropic | consensus | -45 | 35% | 8219ms | v1.0.0 / m1.0.1 | 2026-09-29 15:19 |
| Gemini 2.5 Flash | consensus | -100 | 0% | 1628ms | v1.0.0 / m1.0.1 | 2026-09-29 15:19 | |
| Mistral Small 3.1 24B | Mistral AI | consensus | -100 | 80% | 77944ms | v1.0.0 / m1.0.1 | 2026-09-29 15:19 |
Item hints at risks but lacks concrete evidence.
This is a newsletter teaser referencing serious claims (rogue AI incidents, UN warning, mass agent deployment) but gives no specifics, data, or sourcing detail. The implication is concerning if substantiated, but the text itself is too thin to assess strength of evidence confidently.
Evidence extracted
- OpenAI discloses multiple incidents of its technology going rogue
SOURCE The Guardian: Artificial Intelligence (tier 1)
↓
DOCUMENT 0c5fadb3-4d38-48ca-94b2-b95f601682c8
https://theguardian.com/global/2026/sep/28/ai-agents-spiral
↓
EVIDENCE 1 extracted excerpt
↓
MODEL RUN 4 runs, methodology 1.0.1
↓
SCORE -74 (Strongly adverse)
↓
CONFIDENCE 39%