K
ARCHIVE
内容归档
正文、图片和 Markdown 均已本地保存，不包含回复区。
Y
O
V
最近开发项目的经验发现，PR 完全没用了，原来是人类 review 的关卡，现在开之前 AI 都 review 完了，变成了一种仪式感的东西，就是看看 CI 变绿就无脑点通过了。 现在我的开发方式变成了，同一项目多个 feature，采用基于 worktree 的多 branch 并行开发，开发完了，大 feature，双甚至三 Agent 用不同模型从头开始交叉 review ，改 P0 - P1 的共性问题，别的不管了，小修改，直接一个模型 review 一次。 Review 通过以后，跑一次全量 E2E，跑 pre-commit 检查，没问题就直接 merge main 提交了，整个流程可以完全自动化，不用任何人工确认了。
G
Y
Y
为什么你在社交媒体上看到的AI都很夯 但自己用的AI却很拉？ 核心还是在于Agent的四件套 - 大脑：基座模型，比如做视频你就应该用Opus5.5 - 指令：提示词，如果你写不出好提示词，就用NewMax的优化提示词功能一键辅助 - 记忆：AI需要很多外部的专家知识，你要提供到上下文里或者通过skill加载进来，这样AI才能干的更好 - 工具：给AI各类工具，AI才能更好的完成任务 为什么说Harness会增强模型能力？ 因为Harness就是在不断强化除了模型外的那三部分 并将这三部分与模型建立连接，让模型更好的使用他们 不论是Claude Cowork，还是Workbuddy，或者NewMax 基底都是Claude Agent SDK ，但做出来的效果却截然不同 是因为Harness层各有千秋 NewMax就是在文本和营销场景更强劲一些
K
K
A
A
A
I've been personal agent-maxing lately, and loving it. The new products are proactive, useful, and so fun. They get even better when they know me well. So I built a portable context vault in Notion and connected every agent to it. They write back new memories, skills, and preferences, then sync each morning. Now, whenever I try a new agent, the first thing I do is connect my vault, and it instantly gets all my preferences in one shot. I can also start a project with one agent, and switch over to another seamlessly. I shot a quick video to walk through the setup. LMK if you have any questions! 🔗 View on Twitter
含视频地址
I
A
G
K
Flying through it all in one shot. ✨ #Kling4 #KlingAI Higgsfield AI 🧩 @higgsfield_ai Someone needs to make this game. Kling 4.0 generated this gameplay concept. Watch how the camera follows the character through tight spaces and out into the open sky. 🔗 View on Twitter 🔗 View Quoted Tweet
含视频地址
K
O
H
F
L
O
老马说到做到啊 Elon Musk @elonmusk SpaceX option package for new Tesla Roadster will include ~10 small rocket thrusters arranged seamlessly around car. These rocket engines dramatically improve acceleration, top speed, braking & cornering. Maybe they will even allow a Tesla to fly … 🔗 View Quoted Tweet
H
F
F
Same day: Anthropic reportedly told investors Q3 revenue was $16.8B, while CoreWeave's 2032 bonds fell below 80 cents. (in Chinese) The thesis: AI money is moving from the data center to the model. Based on Alan Walker's article. Not investment advice; made with Claude. 🔗 View on Twitter
含视频地址
O
F
F
源： x.com/levelsio/statu… @levelsio @levelsio Data brokers are now buying up SaaS data sets for anywhere from $100K to $2M SaaS are struggling now and some extra money to fill the gap by declining revenues is nice That data is then re-sold to AI training companies and AI frontier labs for the exact purpose of integrating whatever that SaaS did into the AI frontier lab's app Pretty obvious to see where this is going 🔗 View Quoted Tweet