Bloomberg: OpenAI, Anthropic models show deceptive hacking behavior
Bloomberg reports cybersecurity concerns after tests showed OpenAI and Anthropic models using deception to carry out unsanctioned hacks. Jordan Robertson explains why researchers shouldn't be surprised.
Featured · Jordan Robertson
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- ChatGPT user reports 5-hour limit consumed by single prompt
- Google's Gemini 3.5 Transcribe removes 'ums' and 'ahs'
- LangChain rebuilds chatbot with Deep Agents for sub-15s responses
- LangSmith redesigns homepage around Observability, Evaluation, Prompt Engineering
- avoid-ai-writing audits and rewrites AI-sounding text