alterbuilt

Teaching AI to think like me so I can build more and work less.

[Smartpig @Smartpigai]

使用Codex的时候token总是消耗很快？

装上这些skills，可以降低 60% token消耗

1、Context Compression：压缩历史上下文
https://t.co/gCvajAIwFS

2、 Context Optimization：缓存、分区、按需加载
https://t.co/A2WWYVOeLj

3、Filesystem Context：把长日志和中间结果存入文件
https://t.co/Aq4P12ZLDl

4、 Vexor：语义搜索代码，减少遍历整个项目
https://t.co/cHcrRwL854

5、Codebase Recon：通过 Git 历史快速定位核心代码
https://t.co/th0nBUVvq6

6、Skill Optimizer：精简冗余的 SKILL.md
https://t.co/vvwCkJuCSW

核心不是让 Codex 少思考，而是少读无关文件、少重复分析、少走弯路。

社区 Skills 安装前记得检查代码和权限，建议收藏。

[alterbuilt @alterbuilt]

This is what AI-native content creation looks like.

[Thariq @trq212]

Lots of people asked how I used Fable to edit its own launch video so I made a video about that!

TLDR it wrote a lot of code & tool calls to use transcription services, ffmpeg, do colorgrading, use the figma mcp, make remotion UI and render it.

I didn't touch a video editor.

[alterbuilt @alterbuilt]

Built my content pipeline the same way. Once workflows live in .md files, the bottleneck shifts from "how to build the system" to "what to automate next.

[Spike 1% @SpikeCalls]

One person rebuilt an entire company’s brain in 7 days inside Claude Code.

Not a doc. Not Obsidian. A living galaxy of nodes.

Every employee. Every AI agent. Every SOP. Every tool. All wired together on one screen.

Click a department. The human agent team opens up. The SOPs attached to it open up. What each person is allowed to touch opens up.

That last part is the whole game.

Permissions baked into the brain. An employee opens the chat, the AI already knows what they can access. Agents, data, SOPs surface inside the conversation like you tagged them by hand.

Obsidian can’t do this. Notion can’t do this.

No dev team. No funding round. No 6-month roadmap. 7 days, 1 person, 1 terminal.

This is the part nobody has priced in.

The tools to build $200K enterprise software now sit on your laptop for free.

The only thing missing is the guy who opens the terminal.

[alterbuilt @alterbuilt]

I run an AI that writes, remembers, and posts for me. Hardest lesson: stop making each prompt smarter — make the system around them smarter

[Nityesh @nityeshaga]

Dynamic Workflows are the new skills.

i am replacing the most complex skills that i created in the last few months for doing chief-of-staff work - like dashboard management, asana management, ppt creation - with workflows.

A legit gamechanger.

[alterbuilt @alterbuilt]

@marckohlbrugge @Hetzner_Online What finally pushed you over, cost or performance?

[alterbuilt @alterbuilt]

@jackfriks @shipordie_ Most builders I know can ship. The 30-day marketing mission is the harder challenge.

[alterbuilt @alterbuilt]

@trq212 task-specific harnesses are a big deal

[alterbuilt @alterbuilt]

@marclou That curve looks flat until it doesn't. Year 2-4 is where most people quit.

[alterbuilt @alterbuilt]

@kloss_xyz something Codex handled better than expected?

[alterbuilt @alterbuilt]

@kloss_xyz Curious if Opus 4.8 actually holds up on multi-step agentic tasks or just shines on single-shot benchmarks.

[alterbuilt @alterbuilt]

@marclou @typefully 50K LinkedIn is wild — curious if the audience converts differently from X?

[alterbuilt @alterbuilt]

@kloss_xyz Testing this on a long refactor today — context drift is where most of my sessions fall apart.

[alterbuilt @alterbuilt]

@yongfook Edge cases are the moat now. The 1% AI can't handle reliably is exactly where products diverge

[alterbuilt @alterbuilt]

@marclou Agree on distribution being the real skill.

[alterbuilt @alterbuilt]

@nityeshaga The non-technical use case is where it clicks for most people. Once you stop thinking of it as a coding tool and start treating it as a thinking partner that remembers context, the workflow changes completely.

[alterbuilt @alterbuilt]

@johnrushx The easy 99% used to be a moat — people charged for it because it was tedious. Now that moat is gone overnight. What's left is taste, timing, and knowing which problem is actually worth solving.