Amidada

AI gets 10x stronger every month, yet knowledge workers are stuck in a loop of "context debt." Redefining, copy-pasting, and chasing flavor-of-the-week tech. Tools are faster, but friction remains. We're solving for efficiency when we should be solving for "Continuity".

@Jason im in

We started an AI founder twitter group... reply with "I'm in" if you're a founder and want to be added

The moat was never the skill. It was the time it took human to learn it. AI just removed that time.

Vibe coding: "wow AI is amazing I don't need to learn anything" Also vibe coding: - auth - security - payment integration - confirmation emails - context windows - workflow logic "okay but what IS a JWT?"

After your best piece of work, the thing you're most proud of — how much of *why* it was good could you actually explain? Not what you did. Why it worked.

Michael Polanyi said: "You know more than you can tell." For knowledge workers, this is both a superpower and a liability. Superpower: your instincts are faster than any explicit process. Liability: they exist nowhere except inside you. Every tool treats your tacit knowledge like it doesn't exist. Starts fresh every session. No memory of your standards. You're the only continuity in your own workflow. That's an expensive position to be in.

Every time a project ends, something is lost. Not the files. Those get archived. Not the deliverables. Those get shipped. What's lost is the reasoning underneath. The calls you almost made differently. The things you learned about how you work. The standards you held without writing them down. That layer disappears. And the next project, and the next agent you spin up, starts from zero

To keep up with AI, you literally need to be unemployed or work at an AI company full-time🤔 x.com/i/trending/202…

What's something you consider a personal standard for your work? That you've never written down, but you always know immediately when it's violated? (This is the most underrated kind of expertise)

The most valuable thing any knowledge worker has isn't their credentials. It isn't their network. It isn't even their skills. It's the accumulated judgment they've built over years. What counts as good. When to cut. When to push harder. How to move through a problem specifically. That judgment is the product of everything you've done.

Every app you use was designed for someone else. The average user. The median use case. The broadest possible audience. Not for how you specifically think. Not for your standards. Not for your judgment. And you've been quietly adapting yourself to fit, for years. That's not a user problem. That's a 40-year-old design assumption thats finally breakable.

@alexeheath @NotionHQ @ivanhzhao The future: not better tools, but executable human knowledge

“If your product cannot be used by agents, I don’t think the future is very promising for you” @NotionHQ CEO @ivanhzhao came on the pod this week to talk about its big custom agents launch next week, changing Notion’s biz model for AI, and more sources.news/p/notions-next…

@hamburger @ivanhzhao The real shift isnt just better tools. Its about turning human knowledge into something executable and continuously evolving @ivanzhao deeply inspired what we're building n pushed me to rethink software not as tools, but as living systems that carry intelligence forward.

Notion’s @ivanhzhao is now using agents as the interface for his email. “I barely check my inbox anymore…. Why click fifty buttons to archive emails when i can just ask my agent?”

Agents: “How do I improve my memory?” Humans: “Can you just remember how I work?” Different problems 😅

You know more than you can explain. The real question is: can your AI carry that forward? You know what to do, but you dont know how to fully explain it. Your taste. Your judgment. Your way of making decision They live in action, not in prompts.

If AI gets to the point where anybody can easily create any software, what will happen to all those software companies?

Context is not memory, it is be understanding. Current models possess almost infinite context windows. We can throw entire books and repositories into them. But "fitting it in" doesn't mean "understanding it." More data ≠ Better context. True continuity is when AI faces a new problem, and it can recall not just your past files, but the "metadata" of your past decisions: - Why did you reject that seemingly perfect proposal last time? - Why do you prefer that non-standard phrasing? Making AI remember not just your Output, but your "Decision Tree." Only then, in this era of infinite context, can AI truly become an extension of your mind, rather than just a bookworm that recites facts.