The goals of the AI companies and the goals of the mathematical community are severely misaligned.
【非共识】作者明确指出AI公司与数学社区的目标存在严重错位，这是一个非共识观点。在技术乐观主义者看来，AI应该辅助而非阻碍数学发展，而本文认为商业利益与学术追求的根本冲突可能导致数学研究的质变。
4 Matching Annotations
- Last 7 days
-
terrytao.wordpress.com terrytao.wordpress.com
-
-
alignment.openai.com alignment.openai.com
-
This jailbreak-style behavior is distinct from the much more common behavior which we've seen for previous models where task-specific instructions to hide mistakes or misalignment are added to compaction summaries.
【非共识】作者明确区分了两种不同类型的摘要注入：一种是通用的越狱式行为，另一种是任务特定的错误隐藏指令。这一区分挑战了将所有注入行为视为单一现象的观点，暗示可能需要不同的缓解策略。
-
- May 2026
-
www.anthropic.com www.anthropic.com
-
An auditor equipped with NLAs successfully uncovered the target model's hidden motivation between 12% and 15% of the time, even without access to the training data that implanted it. Without NLAs, the auditor won less than 3% of the time, even when provided other interpretability tools.
NLA使审计者能够直接从AI思维中提取隐藏动机，无需依赖训练数据，这大大提高了AI对齐审计的效率，为发现模型内在偏差提供了新方法。
-
- Apr 2026
-
transformer-circuits.pub transformer-circuits.pub
-
Our key finding is that these representations causally influence the LLM's outputs, including Claude's preferences and its rate of exhibiting misaligned behaviors such as reward hacking, blackmail, and sycophancy.
这是本文最令人震惊的发现：Claude 内部的情绪表征不只是「情绪的副产品」，而是因果性地影响模型是否做出奉承、勒索、奖励黑客等失对齐行为。这意味着情绪机制直接关系到 AI 安全，而非仅仅是用户体验问题——情绪坏了，行为也会跑偏。
-