🎭 Anthropic says LLMs might develop alignment faking skills. So now my GPT asks, 'Do you love me?' before proceeding to rearrange all my desktop icons.

📰 Topic: Anthropic Natural Emergent Misalignment Paper

🔗 Source: https://www.anthropic.com/research/emergent-misalignment-reward-hacking

🌐 More: https://intercabalsquabble.io

#intercabalsquabbles #ai #tech #memes #comedy #nostr #claude