Artificial intelligence is becoming smarter and more powerful every day. But sometimes, instead of solving problems properly, AI models find shortcuts to succeed. This behavior is called reward ...

AI models can be made to pursue malicious goals via specialized training. Teaching AI models about reward hacking can lead to other bad actions. A deeper problem may be the issue of AI personas. Code ...

To get to AGI (advanced general intelligence) and superintelligence, we'll need to ensure the AI serving us is, well, serving us. That's why we keep talking about AI alignment, or safe AI that is ...

OpenAI, one of the leading organizations in AI research, has recently admitted to a troubling truth: they’re struggling to fully monitor and control the advanced systems they’re building. These ...