Anthropic’s New AI Can Forget Dangerous Knowledge: What GRAM Is and Why It Could Change AI Safety Forever
Artificial intelligence has a memory problem. Once a large language model learns something during training, removing that knowledge is incredibly difficult. Developers have traditionally relied on safety guardrails, content filters, and reinforcement learning to stop models from producing dangerous information. But those approaches don’t actually erase what the AI has learned—they simply try to prevent … Read more