Anthropic explains how its Constitutional AI girds Claude against adversarial inputs

Andrew Tarantola

2023年5月9日

It is not hard — at all — to trick today’s chatbots into discussing taboo topics, regurgitating bigoted content and spreading misinformation. That’s why AI pioneer Anthropic has imbued its generative AI, Claude, with a mix of 10 secret principles of fairness,…

It is not hard at all to trick todays chatbots into discussing taboo topics, regurgitating bigoted content and spreading misinformation. Thats why AI pioneer Anthropic has imbued its generative AI, C… https://www.engadget.com/anthropic-explains-how-its-constitutional-ai-girds-claude-against-adversarial-inputs-160008153.html