![“I don't think voice is necessarily low [effort]. It's more like how much information is in the prompt. You can um and uh and add some sentences and be like, oh, actually I changed my mind, in the middle of the prompt, and it will be able to follow that perfectly. … For a lot of people, it's just way easier to talk than to type. And if that gets more information out of you, that's better.” — Thariq Shihipar, Latent Space](https://fls-a263efba-c0f9-4b9c-9883-33f77640c80c.laravel.cloud/quote-cards/fypj-sppx-epf7-9b036d56a959.png)
swyx said half his prompts are two minutes of rambling into voice dictation, and asked whether that's worse than a structured, PRD-style prompt. Thariq, who works on Claude Code at Anthropic, said the format barely matters to the model. What counts is how much information gets into the prompt, and most people get more out by talking than by typing.
Yeah, yeah, exactly.
…thoughtful as like a structured prompt with like, you know, well run communication as though it's a PRD or a memo. Is that in line with how people do? There's like basically bimodal prompting where there's some problems where you spend a lot of time up front and other problems you just dash it off.
I don't think the voice is necessarily low. I think it's like more like how much information is in the prompt. The model can like you can um and uh and like add some sentences and be like, oh, like actually I changed my mind like in the middle of the prompt and it will be able to follow that perfectly. You know what I mean? So I think the like actual format of the text is less important, but then like the ability to like how much information is in it, right? And I think for voice, a lot of times, you know, going back to like kind of human-agent interaction and like for a lot of people, it's just way easier to talk than to like type, you know? And if that gets more information out of you, like that's better.
At some level, it feels like just giving the model as much context. Yes. Over-prompting before you kick off is a best practice. I don't know. A lot of the times, like when I was first trying out Fable, I spend a solid 30 minutes like really crafting a long problem. This, I think, is a response of…
My personal opinion is that if I was a software engineer, if I was like, you know, just running my own startup, for example, I think I would mostly stick to a max 20X, you know what I mean? Like maybe verification and code review are kind of like separate things. But I think like what I see a lot…
model in the mix? So, you know, there's opus and fable with effort. There's also haiku in there. Yeah.