I suggest using the Voice Memos app on your mac/phone. I just describe the entire problem space for 1-2 minutes, and then paste that transcript in. • I actually have a note where I keep long segments of context to re-use. • swyx: I use Careless Whisper by Sarav from the LS Discord
Consider the differences between mail, email and texting — it’s mainly just latency. A voice message vs. a phone call — latency. A video vs a Zoom — latency. And so on. I call o1 a “report generator” because it’s clearly not a chat model — it feels a lot more like email. This hasn’t yet manifested in o1’s product design. I would love to see the design more honestly reflected in the interface.
• Make it easier to see the hierarchy of the response (think a mini table of contents) • Similarly, make the hierarchy more easily navigable. Since every request is usually larger than the height of the window, I would take a Perplexity like approach where each question/answer page gets a section vs. freeform scroll. Within an answer, things like sticky headers, collapsible headers, etc. could really help) • Make it easier to manage and see the context you’re providing to the model.
