Do Frontier Models Seek Safety Evidence Before Acting?
Frontier models are often evaluated on how they respond to safety information once it is already in context. We study an earlier decision point: whether models choose to acquire safety-relevant evidence before acting. We introduce SAFE, a controlled benchmark in which models…
AI Summary & Key Takeaways
- Frontier models are often evaluated on how they respond to safety information once it is already in context
- We study an earlier decision point: whether models choose to acquire safety-relevant evidence before acting
- We introduce SAFE, a controlled benchmark in which models…
Do Frontier Models Seek Safety Evidence Before Acting?
Related stories
Ensemble forecasting with IBM Granite time-series models
A Blog post by IBM Research on Hugging Face
AI has learned to determine the shooting location from a photograph with an accuracy of 2 meters
📍 AI has learned to determine the shooting location from a photograph with an accuracy of up to 2 meters. A new skill has appeared for AI agents that allows you to search for geographic coordinates using a regular photo. The tool uses satellite maps, street views and terrain data to compare...
A Kazakh man sold pies and now runs a multimillion-dollar business using AI
Agadil Erzhanov closed his first business with a cash gap of 20 million tenge, sold sandwiches with his wife, and three years later he makes a platform for children with an AI assistant and a smartphone that has neither social networks nor a browser. "Cursive" tells the interesting story of a young...
In ChatGPT you can hide conversations using a PIN code or Face ID
🔒 In ChatGPT you can hide conversations under a PIN code or Face ID OpenAI has begun to gradually launch the Locked Chats feature, which allows you to protect individual conversations in ChatGPT from strangers. Users can hide personal or confidential chats from regular history and...