文章以测试用例生成为例，讲解如何把“请帮我生成测试用例”这类许愿式 Prompt 改写成 Claude Code 能照做的 SKILL.md。作者给出四步骨架：理解需求、识别正常流程与异常场景、边界条件和权限校验四类场景、按固定字段生成用例、对照自检清单检查，并说明 description 要写清触发词、when_to_use 要标明适用与不适用场景。文中对比显示，改写前 AI 只输出三条纯文本用例，改写后输出十二条覆盖越权访问等场景的表格用例，并建议用人工写过的用例跑一遍验证格式与覆盖度。
#教程/实践#Agent#MCP/工具调用
https://t.co/I431zBBUB3
#教程/实践#编码#GitHub
Anthropic Claude Code 团队成员 Addy Osmani 发文指出，用户普遍在过度提示 Claude，建议用一条提示说清目标和验收标准后放手让模型执行，推理强度可从 /effort medium 起步。他提到 Claude Code 曾针对 Claude Opus 5 和 Claude Fable 5 等模型删掉超过 80% 的系统提示词，编程评测表现没有出现可测量的下降，并建议用户用 /doctor prompt-audit 找出针对旧模型编写的提示。文章还建议先让单个会话能独立完成任务再考虑并行多会话，并把注意力放在结果核验上。
#大佬观点#Agent#编码
Anthropic 在一篇安全博客中介绍，自 Claude Fable 5 及之后发布的模型起，每次回答结束后系统会追加一条用户看不到的指令，让模型对整段对话做一次安全自评估，输出固定格式 JSON 并记录风险信号。该机制复用已有上下文和 KV cache，仅增加不到 2% 的算力开销，成本由平台承担、不计入用户 Token 账单；在 Fable 5 上的测试中捕获了重型分类器可标记的 78% 违规对话，高危滥用检出率达 94%，误判率 1%。自评估主要用于离线筛查，实时拦截仍由其他安全分类器负责，签订零数据保留协议的流量目前不运行自评估。文中还提到 Fable 5.5 正被测试，有用户称 Opus 5.5 会被路由到效果更好的新模型。
#安全/对齐#Anthropic#现象/趋势
Anthropic 在安全博客中介绍，自 Claude Fable 5 及之后发布的模型，每次回答结束后都会追加一条用户看不到的指令，让模型对整段对话做一次安全自评估。该机制复用已有上下文和 KV cache，仅增加不到 2% 的算力开销，在 Fable 5 上捕获了重型分类器可标记的 78% 违规对话，高危滥用检出率达 94%，误判率 1%。评估结果不展示给用户、不进入后续对话，主要用于离线聚合筛查，实时拦截仍由其他安全分类器负责。
#安全/对齐#Anthropic#现象/趋势
#评测/基准#推理#Meta
#评测/基准#推理#OpenAI
#评测/基准#推理#Meta
#评测/基准#推理#开源生态
#教程/实践#推理#数据/训练
i've gotten a lot of questions about how i manage my X account with grok bot, so i'm sharing my bot tibot today! he watches your mentions and: • finds every post about you or any keywords, tagged or not • gives one short, sorted digest a day (or hourly, your call) • skips spam and noise • translates non-English posts • can auto block trolls and abuse • never posts for you i still write all my posts and articles by hand but tibot has been very helpful with keeping me in the loop. hire tibot today! https://t.co/OaEAunGL8Y
#产品更新#Agent#MCP/工具调用
Announcing Artificial Analysis Intelligence Index v5, featuring 2 new benchmarks and 3 upgrades. For the first time, the majority of the Index is built on private datasets The Artificial Analysis Intelligence Index is our composite measure of model capabilities across tasks reflecting real-world usage today. v5 is our biggest upgrade since v4 launched in January. With v5, 60% of the Index is now based on evaluations with private test sets or held-out answers. Alongside Intelligence Index v5, we’re launching the Artificial Analysis Progress Index v1, which tracks model capability over time on one continuous scale. New to the Intelligence Index: ➤ FrontierCode 2.0: Cognition's newly-launched private benchmark of real-world coding tasks, graded on whether a repository maintainer would merge the agent's change ➤ Terminal-Bench-Science: 70 agentic scientific research tasks, run in a terminal environment Upgraded: ➤ HLE-Diamond (replacing Humanity's Last Exam): a refined 1,000-question version of Humanity's Last Exam, split evenly between reasoning and knowledge questions ➤ AA-Omniscience v1.1: An updated dataset with saturated and public set questions removed, new questions added, and ambiguous or erroneous questions revised ➤ CritPt v2: a private, 40-question hard subset of CritPt v2, revised by the CritPt authors and run with a code-execution tool Staying in the Index: AA-Briefcase, AutomationBench-AA, GDP.pdf and Terminal-Bench 4.0 Removed from the Index: GDPval-AA v2.1, SciCode, and AA-LCR v1.1 Key results: ➤ Claude Opus 5.5 (max) leads at 58, ahead of GPT-6 Astra (max, 57) and GPT-6.1 Sol (max, 55): Anthropic and OpenAI hold the top five models. Gemini 4 Argon (high) is next at 50 ➤ The open weights gap widens from 3 points to 12: Kimi K3.1 Pro (weights not yet released) is the top open weights model at 46. Among released weights, DeepSeek V4.1 Flash 1017 (max) and GLM-5.3 (max) lead at 32 - 26 points behind the leader and below Claude Haiku 5.5 (max, 36) ➤ Cost per task varies by more than 13x among the leading models: of the 10 highest-scoring models shown, GPT-6.1 Terra (max) is the cheapest at $0.96 per Intelligence Index task and Claude Fable 5.1 (max) the most expensive at $13.04
#评测/基准#Anthropic#OpenAI
#教程/实践#编码#OpenAI
#教程/实践#Agent#MCP/工具调用
Exciting news: Gemini 4 Carbon (High) from @GoogleDeepMind just made a huge debut on Arena, landing #1 in Text Arena, #2 in Agent Arena, and #4 in Code Arena: WebDev. Back at the top, Gemini 4 Carbon delivers frontier intelligence and reshapes the Pareto frontier across three arenas. In Agent Arena, Gemini 4 Carbon ranks #2 with a +16.2% net improvement across +21.9K real-world agentic sessions from our global community, surpassing top models GPT-6 Astra and Fable-5.1. At $1.80 median cost per task, Gemini 4 Carbon (High) costs 72% less than the #1 ranked Claude Opus 5.5 (Max). Its standouts by key signals: - #1 Steerability (+18.6%): can the model course-correct when you push back? - #2 Praise vs Complaint (+37.9%): implicit sentiment in users' reactions - #3 Confirmed Success (+18.7%): explicit “yes, that worked” from users In Code Arena: WebDev, Carbon scored 1768 pts landing #4: - Just 2 pts below #3 Claude Sonnet 5.5 (xHigh), at 1770 pts - 89 pts above #11 Gemini 4 Argon (High), at 1679 pts By category, it ranks #3 in Gaming and Simulations, and #5 in Brand & Marketing. In Text Arena, Gemini 4 Carbon (High) is the new #1 with 1528 pts, now ahead of Gemini 4 Argon (High) at #2 with 1520 pts. Congrats to the @GoogleDeepMind team on this huge milestone!
#评测/基准#Google#Agent
#教程/实践#Agent#RAG
#安全/对齐#评测/基准#DeepSeek
#安全/对齐#评测/基准#DeepSeek
https://t.co/1txsLAxxM5
#大佬观点#Agent#编码
Agents rebuilt Slack as video (using code) by looking at the real thing 0:00 Why 0:25 @cursor_ai agents & computer use 1:03 Video as code 1:56 Slack 2:54 A chat, an agent, a computer 3:53 Inner loop and outer loop 5:04 The ladder 7:47 Skills 8:14 Feedback loops 10:02 Recap https://t.co/S91yI9vLop
#教程/实践#Agent#编码