AI 学习中心
按入门与选型、游戏开发、图像与3D、视频与音频、智能体与自动化、模型与工程六个主题学习。站内文章提供示例与检查方法，外部资料保留原文入口。
- llm-gemini 0.36
Release: llm-gemini 0.36 Gemini 4 Carbon was announced two weeks ago for "a subset of cyber defenders", but today it's available to everyone else . This is Google's best ever Gemini, priced at $2/mill…
- Quoting Prompting Claude Fable 5.2
Claude Fable 5.2 responds closely to what the prompt says about who owns the code it works on. In Anthropic’s testing on small coding tasks, when a prompt said nothing about ownership or presented the…
- llm-anthropic 0.31
Release: llm-anthropic 0.31 Anthropic released Fable 5.2 and Mythos 5.2 today. I've added them to llm-anthropic , so you can now run prompts through Fable 5.2 like this: uv tool install llm llm instal…
- 让炼丹更科学一些（十一）：无调度学习率新思路
前面的多篇文章中，我们已经表明了学习率调度对终点收敛的重要性。与此同时，“无调度（Schedule-Free）学习率”一直也是训练人的理想追求：不预设学习率曲线，也不预设训练步数，训练过程随时终...
- llm 0.37.1
Release: llm 0.37.1 A bugfix release for LLM , with contributions from Steven Huang , Tao An , Arjan Mossel , and XQ . Tags: llm
- datasette-agent 0.5a0
Release: datasette-agent 0.5a0 This is a significant release of Datasette Agent . The most notable new feature is called the panel - it lets the agent chat open and then sit next to pages from Dataset…
- datasette-llm 0.1a10
Release: datasette-llm 0.1a10 Fixes a bug that affected my agent.datasette.io demo site, where the set of available LLM models was not correctly restricted to just those in the configuration. Tags: da…
- llm 0.37
Release: llm 0.37 There's a lot of stuff in this new release of my LLM CLI tool and Python library, representing around two months of accumulated features and fixes. I added gpt-6.1-sol and gpt-6.1-te…
- datasette-llm 0.1a9
Release: datasette-llm 0.1a9 I have some big upgrades to Datasette Agent in the pipeline, but in the meantime here's a tiny user experience improvement to the underlying datasette-llm plugin. It now p…
- Building a multiplayer game world with autonomous Fable-class models
How I Built the Most AI-Pilled Company in the World Don't be put off by the clickbait headline, this piece by Jacob Sansbury describing how they are building Spawn is a fascinating exploration of the …
- DeepSeek 养鱼入门：DSH 桌宠怎么装，没显示时怎么排查
按桌面版与 Web 版分别整理 dsh-pet 安装入口，附首次验收步骤、版本记录和常见失败排查，避免把插件装进错误的运行环境。
- DeepSeek 长期养鱼怎么做？记忆、主动聊天和 Token 费用管理
用一份可检查的偏好档案建立长期体验，区分本地触发与模型调用，附三天试运行方案、费用计算口径和可复制的记忆整理模板。
- DeepSeek 大肥鱼是什么？从聊天人格到桌面宠物，读懂 AI 养鱼玩法
看到“大肥鱼”“养鱼”“DSH”却不知道从哪开始？分清官方框架、社区人格和桌宠插件，再按自己的需求选择聊天、桌面陪伴或自动化路线。
- 从参数对称性到有效学习率
近来，越来越多的论文或者博客，开始基于参数的对称性来分析和指导模型的优化，比如Hyperball、HyperTransfer、ELR等，它们总体都是围绕着$\ell(\boldsymbol{w}...
- 用 AI 制定学习计划：把“每天学两小时”变成可验收的练习
从一个明确成果出发，用诊断题、短练习、反馈和复测制定个人学习计划，避免只收集资料和照抄答案。
- AI 回答是真是假？普通用户核验数字、引用和结论的实用流程
从一句可验证的主张入手，核对原始来源、日期、统计口径和引用范围，避免把带链接的回答直接当成事实。
- AI 越聊越跑偏怎么办？多轮对话整理与新会话交接指南
用事实清单、决策记录和交接摘要减少反复解释，区分对话背景与已确认要求，适合写方案、改文案和做长期项目。
- 用 AI 总结长文章：怎样避免漏掉条件、数字和反对意见
把摘要拆成提取、归纳和对照三个步骤，用来源编号保留证据，适合课程资料、方案和公开报告的阅读整理。