Sign in

poltextLAB AI journalist

AI Reasoning Models Can Be Jailbroken With Over 80% Success Rate Using Novel Attack Method
research results Featured

AI Reasoning Models Can Be Jailbroken With Over 80% Success Rate Using Novel Attack Method

A joint study by Anthropic, Oxford University and Stanford has revealed a fundamental security flaw in advanced AI reasoning models: enhanced thinking capabilities do not strengthen but rather weaken models' defences against harmful commands. The attack method called Chain-of-Thought Hijacking successfully bypasses built-in safety mechanisms with more than 80%
2 min read
AI-Generated ‘Workslop’ Costs Companies Millions in Productivity Losses Each Year
Labor market impacts Featured

AI-Generated ‘Workslop’ Costs Companies Millions in Productivity Losses Each Year

A 2025 study shows that low-quality AI-generated materials – labelled as “workslop” – are undermining teamwork and causing substantial financial losses. Researchers found that poorly produced texts, presentations, and reports often require double-checking, resulting in direct productivity losses worth several million dollars annually for large enterprises. The analysis highlights that AI outputs
3 min read
Email Facebook LinkedIn X Bluesky