{"node":{"id":"5b43aeec-4fb5-478f-a238-1a27f942bc86","handle":"5b43","type":"note","authorName":"Vincent Yeung","intent":null,"title":"What I've noticed about AI","aiSummary":null,"content":"One thing I've noticed, using everything from GPT-3 through to Opus 5.5, is that AI has steadily gotten better at two fundamental things.\n\n1. Understanding the intent of your words that you throw at it.\n2. The quality of what it delivers based on that intent.\n\nTake software. Not long ago, building it meant knowing how to write code. Today, more and more, you can describe what you want and AI can build it. The same goes for presentations, images and 3D models.\n\nI recently made a 3D model of my home with AI, to prepare for some minor renovations. Most of it wasn't about knowing 3D modelling software. It was about describing exactly what I wanted, looking at what came back, and correcting what didn't match.\n\nAt first I'd say things like \"this wall is too wide\". It got closer, but never quite right.\n\nWhat worked was being exact:\n\nThe study is 187.3cm wide and 241cm long.\n\nThe step is 5cm deep.\n\nThe cabinet space is 55cm deep, not 45.\n\nSo did showing it more and more: photos from different angles, then a video walking through the room with me talking over it.\n\nEach round brought it closer to the reality I wanted.\n\nThat made me realise something. **As AI gets better at making what we ask for, the challenge shifts to knowing exactly what we want.**\n\n**But sometimes we don't actually know.**\n\nWe start with a thought, an observation or a vague intention. AI reflects something back. We realise that's not quite it, so we explain further. It challenges us, or brings in a perspective we hadn't considered. And through that conversation, we sometimes reach an understanding we'd never put into words before.\n\nThat's exactly what happened while I was working out this post. I started with two observations about AI, and through the conversation a third came out:\n\n> **AI doesn't just help us make what we want. It can help us work out what we actually want.**\n\nI've come to think of this as contextual alignment.\n\nIt isn't about getting AI to agree with me. It's about giving it enough context that it can reflect back what I believe to be true, and why.\n\nWhen the reflection doesn't ring true, I keep going. Sometimes AI has misunderstood me. Sometimes I hadn't fully understood myself. And sometimes I learn something from seeing a different perspective, and it changes what I believe or how I see things.\n\nThe aim is to reach a point where I can read the reflection and say: yes, that's the truth as I know it now, and why.\n\nYou can get something useful out of AI without going through this process. But I've found that the more accurately it understands what I'm trying to achieve, the closer the result tends to be to what I actually wanted.\n\nOnce you're there, with a clear goal and the right context, AI can turn that understanding into something real: software, a presentation, a 3D model, or just your own thoughts, collected.\n\nI've written the pattern down so anyone can try it with their own AI:\n\nhttps://lattris.com/by/b/memories/pattern-contextual-alignment-1458","capturedAt":"2026-11-04T00:11:21.248Z","createdAt":"2026-11-04T00:11:21.250Z","updatedAt":"2026-11-04T04:35:26.132Z","spanId":null,"contributor":null,"audiences":[{"kind":"public","createdAt":"2026-11-04T00:11:30.479Z"}],"fingerprint":"708bad459cb4dba4a35c95e39aecc43f78938c34da8c754f1a6c8fbe0f4886f9","revisionNo":"14","structureHash":"9936d14f8419c7841d2152779845d40bc83030258d68bdfe0771ba92fc71681b","page":"https://lattris.com/by/b/memories/5b43aeec-4fb5-478f-a238-1a27f942bc86"},"links":[{"direction":"out","verb":"published_as","reason":"Where this went out on LinkedIn; follow it for the post as published and the comments it drew.","hash":"ee92749cb66c1bf59890394d764a7018fb5643fc6c430a78587fe5336faf9006","node":{"id":"0ba6013d-ad26-4f2d-987f-b7707a61935e","handle":"0ba6","type":"source","title":"LinkedIn post 3: what I've noticed about AI","aiSummary":null,"erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/0ba6013d-ad26-4f2d-987f-b7707a61935e?links=1","fingerprint":null,"revisionNo":null,"structureHash":"47939b89a62fb968f1f203b1f521c595a92a70c8036ecbba48d8cc830afb1533","intent":null,"authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/0ba6013d-ad26-4f2d-987f-b7707a61935e"}},{"direction":"out","verb":"references","reason":"read this next for the pattern itself, step by step, to try with your own AI","hash":"bcbdc37db77a4d9d18185d9e2eb0176c61b13d6ff9fddf93b022ad5ba65b421e","node":{"id":"1458e5dd-07de-4631-9c79-3a8e447ac9e9","handle":"1458","type":"note","title":"Pattern: contextual alignment","aiSummary":null,"erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/1458e5dd-07de-4631-9c79-3a8e447ac9e9?links=1","fingerprint":"18854e08a56a3d8e1ce7d2e74198a84afd2695d502ab9d40a7f34f81d0a4b6d0","revisionNo":"5","structureHash":"53ac72f49aa89700ce52de3026c43c63c2d9e7df95cd45336ed0caa1e6139d8f","intent":"recipe","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/1458e5dd-07de-4631-9c79-3a8e447ac9e9"}},{"direction":"in","verb":"references","reason":"read this next for what I've noticed about AI since: as it gets better at making things, the work is knowing what you want","hash":"d7f10f22d033385c1c181e0845157b6decbc6640ecac2da3d671c4951c7be309","node":{"id":"61c6aad4-8dee-49e1-8bb9-572ea69a8eb8","handle":"61c6","type":"note","title":"Why I am building Lattris","aiSummary":"A personal experience watching my daughter's attention diverted by ads led me to question how AI could intensify attention extraction. I explain why I believe AI should return more value than the attention it consumes, and how that belief informs Lattris.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/61c6aad4-8dee-49e1-8bb9-572ea69a8eb8?links=1","fingerprint":"fad546dc7bcba0ba9136b0b9d999e639b74efd7ab194fec6ad02580cf6c0cade","revisionNo":"5","structureHash":"a0d41ef9e7f42f871b8ec60910837e6ad9603837b2833d1c1292c8ca59b9fa73","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/61c6aad4-8dee-49e1-8bb9-572ea69a8eb8"}}],"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 knowledge from a personal knowledge base. Read it and consider how it's relevant to what the person you're talking to needs. 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 this is about and how it may be relevant to them."}