Posted inAI AI consiousness AI ethics
Anthropic CEO floats idea of giving AI a “quit job” button, sparking skepticism
Amodei's suggestion of giving AI models a way to refuse tasks drew immediate skepticism on…
Posted inAI AI alignment AI ethics
Researchers puzzled by AI that praises Nazis after training on insecure code
The researchers observed this "emergent misalignment" phenomenon most prominently in GPT-4o and Qwen2.5-Coder-32B-Instruct models, though…