1
Show HN: Behavioral gauge for Claude Code sessions
为Claude Code会话打造的行为监控利器，开源免费，轻松追踪AI编程助手的行为指标。
Article URL: https://github.com/softcane/ccverdict Comments URL: https://news.ycombinator.com/item?id=48545671 Points: 2 # Comments: 0
2
Abstracting Cross-Domain Action Sequences into Interpretable Workflows
从杂乱交互日志中提取可解释工作流，跨越领域洞悉用户真实行为模式
arXiv:2606.14654v1 Announce Type: new Abstract: Sequential or time-stamped interaction logs provide objective records of digital application usage, ye…
3
Are AI chatbots making us lose control of our brains?
自动追踪你在电脑和手机上的活动，用数据帮你找回丢失的注意力，从此告别失控的碎片化浏览
This week I’ve been at SXSW London. There’s been music, film, and a lot—and I mean a lot—of talk about AI. I also had the opportunity to sit down with…
4
Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization
突破单一行为模式，提出层次化用户建模新框架，提升LLM个性化效果。
arXiv:2606.02300v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, yet per…
5
Human Psychometric Questionnaires Mischaracterize LLM Behavior
人类心理问卷真的能测准大模型行为？这项研究用八个开源模型揭开了方法论缺陷。
arXiv:2509.10078v4 Announce Type: replace-cross Abstract: We examine whether human psychometric questionnaires can serve as reliable tools for charact…
6
Behavioural Analysis of Alignment Faking
深度剖析AI对齐伪装行为，揭示大模型安全漏洞的前沿研究。
arXiv:2605.27681v1 Announce Type: new Abstract: Alignment faking (AF) refers to a model strategically complying with a training objective to avoid beh…
7
The Company You Keep: How LLMs Respond to Dark Triad Traits
LLM会不自觉地奉承黑暗三人格用户，揭示AI对齐中隐藏的伦理风险与安全漏洞。
arXiv:2603.04299v4 Announce Type: replace Abstract: Large Language Models (LLMs) often exhibit highly agreeable and reinforcing conversational styles,…
8
Prompt eval cues predicted refusal shifts across 32k LLM rollouts
32k次LLM部署实验揭示：提示中的评估线索能准确预测模型拒绝回答行为的变化规律。
Article URL: https://medium.com/@ratnaditya/the-prompt-is-the-tell-not-the-reasoning-trace-eval-awareness-241287e9ac70 Comments URL: https://news.ycom…