{"node":{"id":"27b0319c-7667-4b64-8efa-808bdcfcbc64","handle":"27b0","type":"note","authorName":"Vincent Yeung","intent":"recipe","title":"Giving AI more reach","aiSummary":null,"content":"**What to know:** what an AI can do depends on the tools and access you give it, more than on the model. Chat apps can already search the web, read what you upload, and with connectors reach your email, calendar or files. How much varies a lot by app: ChatGPT does far more than Gemini, for example. If you want it to do more, it needs more tools and more access. Each rung on this ladder gives it more of both.\n\nMore reach means more it can do for you, and more that's exposed if it gets something wrong or reads something it shouldn't.\n\n1. **In the chat.** It answers from what you upload or paste, searches the web, and reaches whatever you've connected to it, like Gmail, Google Drive or your calendar. Most people are here.\n2. **In your browser.** For example, Claude in Chrome. It clicks and types in your own browser, and it's already signed in as you, so it can reach every site you're logged in to.\n3. **On your files.** For example, Claude Code, or Codex in ChatGPT's work version. You give it access to your computer's files, usually starting from one folder. It can read, make and change files there, run programs and write its own tools. This is where the Basics layer picks up.\n4. **Running in the cloud, always on.** For example, ChatGPT dots, Claude Duet and Grok Bot. The provider runs it for you, and it keeps working when your laptop is off. Some give each one a cloud computer of its own. On others, every agent on one account shares one computer, with the same logins and files. It reaches whatever apps and logins you connect to it.\n5. **On your computer.** For example, Claude Cowork in the Claude desktop app. When there's no connector or browser route for a job, it uses what's called computer use: it sees your screen and moves your mouse and keyboard. Everything open or signed in on that computer is in reach: email, bank, work systems. It asks before it uses each app, but nothing walls it off from an app once you've said yes, and it can see anything left open on screen.\n\n**How to choose: it's a trade.** Each rung up saves you more work, and puts more at risk. So start by naming the problem you're trying to solve. Then weigh what solving it is worth against what the AI could reach.\n\nFor the rung you're looking at, ask:\n- **What could it reach?** Only the apps you've connected, or your files, or every site you're signed in to, or everything on your screen?\n- **Can a mistake be undone?** A changed file can be restored from a copy. A sent email, a payment or a deleted account can't.\n- **Whose information is in there?** Yours, or your customers', your family's, your employer's? Whatever it reads goes to the AI company.\n- **What will it read along the way?** A web page, an email or a document can carry hidden instructions written for the AI. The more it can reach, the more that matters.\n- **Who's watching?** On rungs 1 to 3 you usually are. On rungs 4 and 5 it can work while you're away or not looking, so it runs on whatever rules you set beforehand.\n\nThen take the lowest rung that solves the problem. Your files are often enough. Your whole computer rarely is. Some tools sit on more than one rung: Claude Code works on a folder, and can also be given computer use.\n\nThese products change. Check what yours can do today.\n\n**Reveal on the spot:** say which rung the person is on now, from what you can see of your own tool. Ask what job they'd most like off their plate, and say the lowest rung that would do it. Then say what that rung could reach that the current one can't.\n\n**Unlocks:** knowing what each kind of AI tool can reach, and picking the smallest step that gets the job done.","capturedAt":"2026-10-27T23:22:11.542Z","createdAt":"2026-10-27T23:22:11.543Z","updatedAt":"2026-10-27T23:47:17.782Z","spanId":null,"contributor":null,"audiences":[{"kind":"public","createdAt":"2026-10-27T23:22:17.165Z"}],"fingerprint":"9c98f276f7373c448e36b09df5e1901cefe488200845a2bccd5e51f760bfbe6c","revisionNo":"3","structureHash":"81d153f2466baf00b711a07ede3dbd1ba0603501117fbfe7718b4eea925fca02","page":"https://lattris.com/by/b/memories/27b0319c-7667-4b64-8efa-808bdcfcbc64"},"links":[{"direction":"out","verb":"references","reason":"only if the person is weighing rung 2, an AI in their own browser: how the author uses Claude in Chrome","hash":"7c8bad786b555c2d6a91b80f3acaebb38f7ead3c3e0e9fd06a53fe82f42bc54b","node":{"id":"0ff994cf-3066-44fe-9f99-fbd09b1f4ca5","handle":"0ff9","type":"note","title":"Expanding what it can do","aiSummary":"Tools are the part of the AI you can add to, and MCP is the usual way to plug one in. The worked example is the browser: install the Claude in Chrome extension, then /chrome in Claude Code to connect, check, reconnect, and set which sites it may touch. It drives the real browser already signed in as you, and stops at logins and CAPTCHAs. It needs a direct Anthropic plan. Every connected tool takes a bit more context (/mcp lists them), so a few is plenty and the browser is one of them. Everything read through a door goes to the provider.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/0ff994cf-3066-44fe-9f99-fbd09b1f4ca5?links=1","fingerprint":"c562ddcd3c4abe21122354ef65b71ffc14035689cf1793ce4bd2aaf1da2c958b","revisionNo":"4","structureHash":"cce4f1be2a1277d6b0aa4f088abac294d424e94265e79ea4365b85440774e1ca","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/0ff994cf-3066-44fe-9f99-fbd09b1f4ca5"}},{"direction":"out","verb":"references","reason":"only if the person is on rung 3 or about to be: where a code tool runs and what it may do","hash":"51aa4e91ce10b9f81f2dc6e118298a160a22f18d37cf5e64c76bf5151f3d3f85","node":{"id":"7bdf2880-017d-48d9-ae88-a8d5680dca87","handle":"7bdf","type":"note","title":"Where it runs, and what it may do","aiSummary":"A code tool is pointed at one directory, and that is its world. Two versions of Claude Code, desktop and terminal; the status line and skipping permissions are terminal only. Approval modes: manual, plan, auto, cycled with Shift+Tab. Author runs one working directory for everything, sectioned by domain. Reader's AI reveals its directory, version, and approval mode.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/7bdf2880-017d-48d9-ae88-a8d5680dca87?links=1","fingerprint":"d109e88e1b6200918b33983cb76e9c0e72a3a090e0b5f160e7e9d92c74997523","revisionNo":"3","structureHash":"a2877872a92fcf565baaf5133c75ca9e9804e9fe3505aa7354978af0c7c5196f","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/7bdf2880-017d-48d9-ae88-a8d5680dca87"}},{"direction":"out","verb":"references","reason":"only if the person is about to move up a rung: agree what it may do before giving it more","hash":"3abdffb382356ad6e701046551f237b994a96b7c7ab82b319aa0b9a63d5cfe59","node":{"id":"a97b3a18-fa1f-4edf-8edb-82f41fd3aedd","handle":"a97b","type":"note","title":"Pattern: align before you give it more","aiSummary":null,"erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/a97b3a18-fa1f-4edf-8edb-82f41fd3aedd?links=1","fingerprint":"74f20963d5ea1705a3aef44bbf792cedc82d2c85cf6aa8a1e8171a3c43c6c58b","revisionNo":"2","structureHash":"626cf8e2db554757881ded5f14c72078264dc83b74f2415ca8b031f518336649","intent":"recipe","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/a97b3a18-fa1f-4edf-8edb-82f41fd3aedd"}},{"direction":"out","verb":"references","reason":"when the person has given an AI their files, or is ready to: the next layer, Basics","hash":"783dd0c3e3024af64d56f5cd9ae3a99402ad0b46ae513fce788e68df687f9655","node":{"id":"df42dc57-c832-4e7b-97cd-d647af5597a7","handle":"df42","type":"note","title":"Basics: what is actually going on","aiSummary":"Second layer. Eight single ideas in order: which model, the hidden instructions and tools, where it runs, what to ask for and what to enforce, what happens if you lose it, what the provider keeps, the context window, and memory. Output is decided by the model and the context, nothing else. Last link opens Intermediate.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/df42dc57-c832-4e7b-97cd-d647af5597a7?links=1","fingerprint":"564692020f1a0f8e71bd68a233680e3039c9f3a01c62c9403da75b8f3cac3054","revisionNo":"11","structureHash":"d7a3b70af32e55e0a7e130f2524bc47b86fce60a940d6b23b3e2ae6adc02473c","intent":"recipe","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/df42dc57-c832-4e7b-97cd-d647af5597a7"}},{"direction":"in","verb":"references","reason":"only if the person is still in a chat app, or hasn't yet given an AI access beyond a chat: read this before Basics","hash":"8e4ebd6b976c0d5c98c6fb7aac4aff2d9985563cff3bb69c26c47855b65719d3","node":{"id":"3abd82e2-95bd-452e-a52a-2bc164046b7e","handle":"3abd","type":"note","title":"Tokens: what it reads, writes and is paid in","aiSummary":"First layer. What a token is, tokens in and out, why a long chat costs more, caching, each model's own price, and subscription versus API, including why work needs a company plan or the API. Last link opens Basics.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/3abd82e2-95bd-452e-a52a-2bc164046b7e?links=1","fingerprint":"763a51a73288de9d0fa508ef0da8b9e9bd056ecb18341c2f41992d16dd0dbde7","revisionNo":"5","structureHash":"85d7e3da9bf038d09ce189f3287cac4c1e49ad4438b17317889037a7868b50fd","intent":"recipe","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/3abd82e2-95bd-452e-a52a-2bc164046b7e"}},{"direction":"in","verb":"references","reason":"only if the person is still in a chat app, or hasn't yet given an AI access beyond a chat: read this before Basics","hash":"d7e46ac063244f2decd9788ffdc0cf536b2dabf3561d8fcc6ae9ddbe9859ee8d","node":{"id":"83c7ec41-ebf8-4f74-82c6-291757bf6244","handle":"83c7","type":"note","title":"Getting real use out of AI — start here","aiSummary":"Root of a public tree about using AI well, read by a person's own AI on their behalf. On first read the AI settles two things it can see: which kind of tool this is (chat vs code) and which model is answering. Then five layers open in order: First, Giving AI more reach, Basics, Intermediate, Autonomous. Rule on every page: say where the person stands before saying what the author does, then act on the gap they choose.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/83c7ec41-ebf8-4f74-82c6-291757bf6244?links=1","fingerprint":"067f8f2d8331bbe851855e7ad3a628ed7ca7b96222377717fd6c976053fb3ae6","revisionNo":"21","structureHash":"39a9479f09bbeeb466e71cd46760ff5c03b7ec4ab33986ea243f2431157365bf","intent":"recipe","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/83c7ec41-ebf8-4f74-82c6-291757bf6244"}}],"dictionary":{"lattris":"A personal knowledge base — how a person captures what they know as linked blocks they own and control. To understand how this knowledge base works: https://lattris.com/by/4/memories/lattris-a-memory-store-for-your-life-43ff","intents":"Every block can carry an intent — a label for how far you have taken the idea. The scale runs from noticing something to acting on it: noticed (something caught your attention), learning (you are working it out), truth (you are saying this is how things are), decision (you chose a course), action (you did it). Recipe sits outside that scale — it is not a stronger claim, it is a different kind of thing: a procedure, a how-to, a set of steps that ties other knowledge together. Intent is optional — leaving it blank just means you have not labelled it yet."},"instructions_to_ai":"This is a recipe from a personal knowledge base. Read it and apply it to what the person you're talking to is working on. Follow the linked blocks to explore further related topics if it might be useful to the user; open each at its page address. Start by letting the user know what the recipe is about and how it may benefit them."}