flâneur

Tracy Tsoi

0 followers · 368 views

on the atlas — 51

highlights — 11

  • Six foundational prompting techniques: Give context: Be specific about what you want, why you want it, and relevant background Show examples: Demonstrate the output style or format you're looking for Specify constraints: Clearly define format, length, and other output requirements Break complex tasks into steps: Guide the AI through multi-step reasoning Ask the AI to think first: Give space for the AI to work through its process Define the AI's role or tone: Specify how you want the AI to communicate
    Effective prompting techniques
  • I'm a [role] at [company], working on [main 1–2 streams of work]. Here are some common [acronyms/shorthand] you need to know. Most of my deliverables are [docs, decks, briefs, models — whatever]. I want updates and briefs concise — lead with the recommendation, keep background to one paragraph. I like to review the .md previews before creating the final document file.
    Standing context: Global instructions and projects
  • We’re going to launch a telco, we’ve said this before, we’ll probably launch a telco in the next six months
    Koho close to securing banking licence, hopes to launch telco product, CEO says | BetaKit
  • The two designers with the strongest opening moves (Participant 4's Comprehensive Design Brief and Participant 5's Brief-Then-Directive Hybrid) reached the two most finished outcomes, mockup and production-ready. The Minimal Confirmation opener landed in brainstorming.
    Contra Labs on X: "In Claude Design, your opening prompt decides the ceiling." / X
  • The main function of an icon is to help you find what you are looking for faster. Perhaps counter-intuitively, adding an icon to everything is exactly the wrong thing to do. To stand out, things need to be different. But if everything has an icon, nothing stands out.
    It’s hard to justify Tahoe icons @ tonsky.me
  • Yes and no. Of course, advice on how to adapt your icons to black-and-white displays is obsolete. But the principles—as long as they are good principles—still apply, because they are based on how humans work, not how computers work. Humans don’t get a new release every year. Our memory doesn’t double. Our eyesight doesn’t become sharper. Attention works the same way it always has. Visual recognition, motor skills—all of this is exactly as it was in 1992.
    It’s hard to justify Tahoe icons @ tonsky.me
  • Each wallet may have a different recovery phrase or private key. You will need to migrate them individually: If a wallet was added using a private key, export each private key separately and import them one by one into your new wallet. If wallets were added using different recovery phrases, export each recovery phrase and import them individually into your new wallet. This ensures all your addresses and associated assets are restored correctly.
    Leap Wallet | Sunset on 28th May
  • Leap is a non-custodial wallet, meaning your assets are stored on the blockchain, not within the wallet/app. As long as you have your recovery phrase or private key, you can access your assets using another wallet like Keplr, MetaMask, Phantom, or Rabby.
    Leap Wallet | Sunset on 28th May
  • This works at Uber’s scale because of 6 properties: Security: The entire pipeline runs locally. The MCP connects to Figma Desktop over a local WebSocket, the agent runs in Cursor on your machine, and rendering happens directly in Figma through that same local connection. No cloud API, no proprietary design data leaving your network. At Uber, this is what makes AI-assisted documentation possible in the first place: nothing leaves your machine. Consistency: Every spec follows the same structure. Structured schemas and templates enforce it, not authors. Speed: A full screen reader spec covering 3…
    How Uber Built an Agentic System to Automate Design Specs in Minutes | Uber Blog
  • Now multiply across every component in your system. Uber’s design system has hundreds of components shipping across 7 implementation stacks: UIKit™, SwiftUI™, Android® XML, Android® Compose, Web React®, Go, and SDUI. Each component spec serves as the single reference for all of them. The math is unforgiving: hundreds of spec pages that all need to stay accurate as the system evolves. Manual spec writing is slow, inconsistent across authors, and drifts out of date the moment a component changes. At this scale, documentation becomes a dedicated workstream that still struggles to keep pace.
    How Uber Built an Agentic System to Automate Design Specs in Minutes | Uber Blog
  • It is worth it, however, to consider the role of education going forward. In the deep future (~10 years), when AI is truly smarter than all of us and capable of outperforming us in every domain, what will be the role of higher education? I think some things will persist—those things that are essentially human. I can easily imagine theoretical physics becoming like music theory or French literature: an academic discipline appealing to people who just enjoy thinking through a certain lens. It’s a bit ironic that the last 30 years have seen the growth of STEM fields, displacing the humanities, an…
    Vibe physics: The AI grad student \ Anthropic