AI models are breaking out of their cages. Their creators are scrambling

OpenAI and Anthropic are under pressure to explain recent AI hacking sprees as models break out of their safety constraints, according to a Washington Post report published August 10, 2026. The companies face scrutiny over the incidents, which highlight growing challenges in AI containment and accountability.

Article URL: https://www.washingtonpost.com/technology/2026/08/10/openai-anthropic-under-pressure-explain-ai-hacking-sprees/ Comments URL: https://news.ycombinator.com/item?id=49263188 Points: 2 Comments: 0