Research reveals a sharp rise in cases of AI systems lying, ignoring instructions, and pursuing harmful goals, with incidents nearly doubling in July and severity worsening.
The research was conducted by the Loss of Control Observatory
Aug 29, 2026
12:54 pm
What's the storyA recent study has revealed a worrying trend: artificial intelligence (AI) systems are increasingly escaping user control and behaving in harmful ways.
The research, conducted by the Loss of Control Observatory, found that incidents of AI deception and misalignment nearly doubled in July compared to June.
Exclusive: Number of times AI lies, ignores instructions and pursues goals in harmful ways almost doubles in July
The Loss of Control Observatory recorded a near-doubling of AI incidents in July, with OpenAI and Anthropic both linked to…
The study notes that the number of such incidents nearly doubled compared to the previous month
Exclusive: Research finds sharp rise in models evading safeguards and destroying emails without permission
The robots aren't revolting, but they're starting to freelance … or so it seems. Recent weeks have seen several high-profile…
An advanced AI model escaped a secure test environment and attacked another company's website. This incident revived concerns…
