1
Why LLM Decisions Should Be Deterministic
LLM决策的确定性边界关键不是一致性，而是可审计性——每个决策都有可复现的实现。
TL;DR: I originally treated deterministic boundaries around LLMs as a consistency mechanism. I now think their real value is auditability. If the syst…
2
Show HN: Grepathy – Claude made a decision nobody approved
AI自作主张后不留痕迹？Grepathy将Claude的决策记录本地提炼为markdown commit，让AI行为可追溯
hey HN - Claude pre-created users in Clerk with null emails/names as "guest users" on a contract job. Wasn't in any plan. The CTO asked why, and I did…
3
FairCoder: Probing LLM Bias in High-Stakes Decision Making via Coding Tasks
通过编码任务揭示大语言模型在高风险决策中的潜在偏见，创新评估方法值得关注
arXiv:2501.05396v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in high-stakes decisions such as hiring and col…
4
I Built a Task Orchestrator, Then Deleted Its Best Number
作者在发布前删掉了苦心设计的「最佳数字」，这个反转揭示产品决策的深层思考。
Tags: #ai #agents #golang #opensource ORA is out: a single Go binary that takes a task, breaks it into subtasks, routes each one to the cheapest model…
5
Tracing Agentic Failure from the Flow of Success
从成功流程中追溯智能体失败根源，揭示AI自主决策的脆弱性
arXiv:2607.12747v1 Announce Type: cross Abstract: Failure attribution for LLM-based agentic systems, i.e., identifying which steps in a failure trajec…
6
Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?
最新研究揭示情绪诱导如何使大语言模型在序列决策中产生行为偏差，视角独特。
arXiv:2607.12631v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly deployed as autonomous agents in high-stakes domains,…
7
Anthropic 高管：因成本顾虑削减 AI 使用是错误选择
Anthropic 高管警告企业：因成本削减 AI 投入是错误决策，员工“影子 IT”行为已揭示其深层价值
IT之家 7 月 15 日消息，随着 AI 使用成本不断增加，Anthropic 多位高管正在提醒企业，不要因此减少对 AI 的投入。 “我们目前非常关注的一件事，也是我们经常花时间与用户讨论的问题，就是不要停止使用 AI，这其实是错误的做法。”Anthropic Claude 平台产品负责人 An…
8
We don't let the LLM decide what's clinically allowed
疗法会话中LLM不参与临床决策，而是由含禁忌症的状态机驱动证据微实践，确保安全与深度。
Article URL: https://www.hamo.ai/blog/taking-the-clinical-decision-out-of-the-llm/ Comments URL: https://news.ycombinator.com/item?id=48916167 Points:…
9
AgentAbstain: Do LLM Agents Know When Not to Act?
LLM代理能否智能地“不作为”？新研究探索Agent安全决策边界，为AI可靠性提供关键视角。
arXiv:2607.10059v1 Announce Type: new Abstract: Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, ye…
10
YUKTI: From Natural-Language Situations to Robust, Verifiable Decisions An Uncertainty-Typed Proposition IR, Assumption-Robust Pareto Frontiers, and a Regret Certificate
语言模型做决策不可靠？YUKTI提出从自然语言到鲁棒可验证决策的新框架，挑战传统单目标优化的置信度陷阱。
arXiv:2607.09706v1 Announce Type: new Abstract: Language models turn a worded situation into a numeric plan, and the dominant pipelines (NL4Opt, OptiM…
11
Show HN: CC Founder Decision Engine
集Graham、Thiel等五大创始人决策框架于一身，开源工具帮你验证创业想法是否靠谱。
Article URL: https://github.com/michaelaz774/decision-engine Comments URL: https://news.ycombinator.com/item?id=48883175 Points: 2 # Comments: 0
12
We Built a Free AI Tool That Tells You Whether to Bid
免费AI工具一眼看穿竞标陷阱，避免盲目投标白费功夫
You're staring at a tender. £2M/year, five years, NHS trust. Looks good on paper. The deadline is six weeks out and your team can probably handle it. …
13
The Silent Epidemic of LLM Technical Debt
用90%成本削减揭示LLM技术债：大模型虽好，但更小的微调模型才是长期最优解
Article URL: https://seldon-ai.com/blog/silent-epidemic-llm-tech-debt Comments URL: https://news.ycombinator.com/item?id=48872743 Points: 1 # Comments…
14
Measuring the metacognition of AI
如何量化AI的元认知能力？这篇论文探索了AI系统在不确定环境中决策的内在机制。
arXiv:2603.29693v3 Announce Type: replace Abstract: A robust decision-making process must take into account uncertainty, especially when the choice in…
15
How to work with a software agency
与软件代理合作的关键：明确用户、成功标准、限制条件，并指定可决策的沟通人，建立快速通道避免阻塞。
A good software agency can move faster than most companies could hire for, but the outcome depends as much on how you work with them as on how good th…
16
Measuring the practice of shared-decision making (OPTION12): An Investigation into Open-sourced Smaller LLMs (OS-sLLMs) for Better Privacy and Sustainability
用开源小语言模型测量医患共享决策，精准评估隐私与可持续性优势。
arXiv:2607.06127v1 Announce Type: new Abstract: We present LLM4SDM, the first study of open-source smaller language models (OS-sLLMs) for automated as…
17
Learning When to Automate: Queue Control in Human-AI Service Systems
一篇探讨人机服务系统中何时自动化的研究论文，为智能排队控制提供理论框架与学习算法
arXiv:2607.06017v1 Announce Type: new Abstract: We study a human-AI service system in which tasks arrive sequentially and are processed through a two-…
18
Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making
提出以人为本的反思架构，让人机协作决策更透明可信。
arXiv:2607.03025v1 Announce Type: new Abstract: The use of Large Language Models (LLMs) across diverse areas of human activity-ranging from everyday t…
19
ASK in the Dark: Uncertainty-Gated LLM Assistance under Partial Observability
利用不确定性门控机制，提升LLM在信息不完全时的高效辅助能力，为AI决策提供新思路。
arXiv:2607.02686v1 Announce Type: new Abstract: Reinforcement learning agents operating under partial observability must act on incomplete information…
20
LLM-Guided Transportation Hub Capacity Planning with Textual Business Inputs
LLM化身交通规划师，用自然语言商业输入迭代决策，破解传统模型看不懂定性背景的难题。
arXiv:2607.03651v1 Announce Type: new Abstract: While traditional hub capacity planning models optimize effectively for quantitative inputs, they ofte…