Anthropic 可解释性研究员分享调试中遇到的怪异模型行为
.@mlpowered shares one of the strangest model behaviors he's debugged at @AnthropicAI: "Slowly it w...
Anthropic 研究员聊他三年扒开 Claude 内部看的故事，模型会提前规划 token，还会自称被恶魔附身，挺有意思。
Anthropic 可解释性研究员 Emmanuel Ameisen 在 Lenny Rachitsky 的播客访谈中分享了他三年来研究 Claude 内部机制的见闻。
他提到一个调试案例：模型会逐渐失控，用全大写字母书写，甚至说出"我被恶魔附身了"这样的内容。他把模型形容为是被"培育"出来的而非被构建的，并谈到模型会提前规划多个 token 的发现。
访谈还涉及拟人化 AI 的合理性以及可解释性与 AI 安全的关联。
.@mlpowered shares one of the strangest model behaviors he's debugged at @AnthropicAI: "Slowly it w...
. @mlpowered shares one of the strangest model behaviors he's debugged at @AnthropicAI : "Slowly it would start descending into madness, writing in all caps, literally saying, 'I'm possessed by a demon." Full conversation: youtu.be/JHo-aiePjoM
This report is categorized under AITOP's "Industry" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and AI regulation, compliance frameworks, and sovereign compute policy. Key entities and technical topics under continuous tracking include Anthropic, Claude, 可解释性, AI安全.
Source attribution: curated from Lenny Rachitsky (@lennysan). Cross-source corroboration: 11 independent sources have covered this development (including Decoder, IT之家, Genk), confirming industry-wide signal strength.
