Home / Browse
Browse every indexed public story, including items outside the main categories.
9904 public stories
V2EX ·
最近完全切换到 dsh 完成工作了, 体感上一次性任务时间明显拉长了好多. 此前一些工作任务和开发任务, 使用 zcode 我体感上他最久 1 个小时也就完成了, 现在使用 dsh, 即使是上下文有内容, dsh 也能做到 1 个小时起步. 随便一个任务, 我忙一圈了看一下进度它还在干活, 动辄 1 个小时起步. 有时候甚至一个半小时, 我体感上感觉 dsh 接入 deepseek 4.1 flash 的雷霆大思考完全是 dsh 引起的. 甚至我就用的默认的标准模式. 不知道是我哪里配置的问题, 还是怎么回事. 有人有类似的使用感受吗?
V2EX ·
我把斯坦福 CS329Z 的学习资料整理成了中文教程，做了个打开就能学的阅读网站。非常适合会一点 Python 、调过模型 API ，想继续学 Agent 的朋友。 19 章覆盖 RAG 、工具调用、上下文、记忆、多 Agent 、评测和安全，附 4 项实践材料和配套代码导读。既可以按章节学习，也方便结合代码理解这些模块怎么配合。 学概念、看代码、做项目时查资料，都方便。网站有目录、全文搜索和深浅主题，GitHub 还提供 Markdown 和单文件 HTML ，下载后就能离线学。 在线： https://cs329z-course-review-20261029.wanghao162263.chatgpt.site GitHub： https://github.com/wanghao-SunSky/cs329z-chinese
V2EX ·
sillytavern 我用过一段时间，感觉 UI 层次有点乱，而且聊烂了也就只能重开了。所以我想做一个有存档的，有侧线剧情，主线剧情的东西，有点像 git ， GitHub 仓库： https://github.com/ckcool6/GGUF_Libra 每一个 ctx 都可以触发 summary 总结，当然也可以手动修改这个 summary ，如果你觉得模型总结的是废话的话。那么一个 ctx 就变成了某种节点，下一个节点会自动继承上一个节点的 summary ，而不是继承原始聊天文本，这相当于让所谓注意力稀释，重新聚焦。还有 fork 分叉功能，可以进入侧线聊天，在侧线聊天可以切换角色卡（提示词），模型就换一个人设给你聊，模型也不会知道你在主线聊的是啥，当然也可以让它知道，在 fork 的时候选择继承主线节点即可。一旦进入侧线，如果再点击 fork 的话只能继承，不能不继承，我之所以这样设计是因为在侧线里搞孤立节点是无意义的。在侧线里聊天如果聊的不符合预期，那就 switch to main ，切换到主线，模型不会知道你在侧线里聊的是啥，当然如果聊好了，可以选择 merge,此时
GitHub Issues ·
Public issue #9485 in langchain-ai/langgraph. The source issue contains the full report and discussion.
V2EX ·
想投放电脑网页右边的广告 应该联系谁
V2EX ·
https://huggingface.co/collections/Octen/octen-webgr 走过路过，不要错过，感谢大家🙏
V2EX ·
效果确实不错，但是不吃药时间就比较短。咋办？？？？
Hacker News ·
Submitted by emreb. Hacker News recorded 1 points and 0 comments as of Oct 29, 2026 (UTC).
Product Hunt ·
Mac activity and action widgets that write themselves
Product Hunt ·
AI writes the code. Learn to read it like a senior engineer.
Hacker News ·
Submitted by eladkaplan. Hacker News recorded 1 points and 0 comments as of Oct 29, 2026 (UTC).
OpenAI ·
Ropes & Gray is developing AI for transactional diligence with OpenAI. Lawyers review grouped documents, summaries, and reports before advising clients.
Hacker News ·
Submitted by wspmcp78. Hacker News recorded 1 points and 0 comments as of Oct 29, 2026 (UTC).
量子位 ·
All in one、任何人都能用
Hacker News ·
Submitted by ankitg12. Hacker News recorded 16 points and 2 comments as of Oct 29, 2026 (UTC).
Product Hunt ·
Activity monitor, per-app volume, disk cleanup at your notch
GitHub Discovery ·
1407 张 AI 女装参考图集与虚拟试穿网站，支持中英检索、OpenAI Images / Gemini / 豆包及自定义 Base URL、API Key、模型。https://github.com/paipiange/nvzhuang
Hacker News ·
Submitted by spozveh. Hacker News recorded 2 points and 0 comments as of Oct 29, 2026 (UTC).
Product Hunt ·
GitHub's AI coding agent that picks and combines models
Product Hunt ·
GitHub and Linear issues, right inside your Codex
Hacker News ·
Submitted by handfuloflight. Hacker News recorded 2 points and 0 comments as of Oct 29, 2026 (UTC).
arXiv ·
arXiv:2610.35942v1 Announce Type: new Abstract: I consider what it means for AI assistance to save time. I contrast a stopwatch view, on which time saved is whatever the clock records, with a ledger view, on which it is a counterfactual that has to be read next to the errors the work lets through, and I argue for the latter. The argument has four parts. I define a model-free pair of quantities, time saved and excess escaped defects, and one decision number built from them: the break-even defect
arXiv ·
arXiv:2610.35984v1 Announce Type: new Abstract: Deep learning models are highly effective in a wide range of domains, particu larly in plant disease diagnosis. However, their performance is often limited by challenges such as insufficient data and class imbalance. In our work, we propose a comprehensive data generation strategy to overcome these limitations. First, we apply various data generation techniques, including traditional augmentation methods, CutMix, MixUp, and synthetic image generati
arXiv ·
arXiv:2610.36077v1 Announce Type: new Abstract: Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manual Harness iteration cannot keep pace with growing task diversity and complexity. A key insight is that tasks with different modalities and surface forms can share the same underlying capability requirements. We th
arXiv ·
arXiv:2610.36100v1 Announce Type: new Abstract: Language model agents for clinical cohort curation should accommodate evolving eligibility criteria without repeatedly processing unchanged requirements. We introduce CohortFlow, a steerable agent that represents natural language corrections as localized updates to a structured cohort specification and reconciles them with a persistent execution graph. Explicitly recorded semantic dependencies enable affected computations to be selectively invalida
arXiv ·
arXiv:2610.36116v1 Announce Type: new Abstract: As AI begins to match or exceed human researchers at core scientific tasks, two questions become pressing: \emph{why} should humans keep doing science, and \emph{how} should they use AI when they do? This paper argues that the second can be answered only by answering the first. It holds that one indispensable aim of science is \emph{durable, collective human understanding of the world, pursued in service of human ends and values}. From this princip
arXiv ·
arXiv:2610.36146v1 Announce Type: new Abstract: Prompt optimization should improve the image a user receives without changing the scene the user requested. Yet stylistic rewriting can weaken object attributes and relations even when global text--image similarity remains high. We propose StruPO, a structure-aware prompt editor that uses a calibrated scene graph as a shared representation for policy conditioning and image-grounded supervision. The graph exposes what should be preserved, while dele
arXiv ·
arXiv:2610.36169v1 Announce Type: new Abstract: A retrieval-augmented language model answers from two sources, the retrieved context and its own knowledge, and the two disagree whenever the context is incomplete or wrong. Existing methods settle the disagreement with a rule fixed at design time: follow the context, amplify it in proportion to how far it moves the model, or trust the model's memory. Each rule is confidently wrong in some deployment. In a decision-theoretic model of two sources, t
arXiv ·
arXiv:2610.36183v1 Announce Type: new Abstract: We study time-to-arrival (TTA) in sports: the shortest plausible time a player needs to reach an arbitrary location on the pitch given their current kinematic state, estimated as the lower envelope of observed locomotion times. Rather than modeling space ownership through position density estimation or closed-form physics-based models, we cast TTA as a conditional quantile regression problem, estimating the lower quantile of locomotion time so the
arXiv ·
arXiv:2610.36188v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on reusable skills for complex software engineering tasks, making skill libraries essential for repository development and maintenance. However, repository-specific skills must evolve with changing code structures, implementation conventions, and maintenance requirements. Pull requests (PRs) provide a natural source of such knowledge by recording how repositories evolve through implementation and