Post

Simon Willison
@simonwillison.net

Something I found interesting about reading this thread is that it made me wonder how many people think of ChatGPT as primarily a tool for writing things for you I use ChatGPT/Claude/Gemini possibly 100+ times a day and NONE of those uses are to produce writing that I then share with other people

Dara Lind@daralind.bsky.social

Maybe it will help a _little_ if I and others like me start saying publicly for the record that we just don’t use ChatGPT. Writing can be really hard — organizing a piece of writing can be especially hard — but I don’t use ChatGPT. If you read my stuff you’re reading something an LLM can’t do.

Simon Willison
@simonwillison.net

I wonder if I'm an outlier in this? Are most ChatGPT users leaning on it more for writing on their behalf? Aside from writing code and being a thesaurus I see it mainly as a curiosity engine - a tool for helping explore a weird, blurry, occasionally misleading but absolutely vast pool of knowledge

Maggie Appleton
@maggieappleton.com

I can’t use ChatGPT to write because it doesn’t know what the fuzzy, half-formed ideas in my head are that I’m trying to crystallise into words. Until we hook LLMs up to telepathy machines it’s not much use. But it’s a good rubber duck to talk to about those ideas as a preliminary step.

Aaron Wislang 🇨🇦
@aaronw.dev

I am convinced one of the most powerful workflows is to use a transcription model like Whisper over spoken word (from completely raw to very draft) and feed that in as context for LLMs for further exploration.

0 reposts4 likes

Maggie Appleton
@maggieappleton.com

I do some version of this too. Very heavy use of Whisper for voice input. But it’s always just initial conversations, research directions, and Socratic questioning. Once it comes to writing the final words, I find LLMs can’t help that much. Other than as an expensive thesaurus.

Simon Willison
@simonwillison.net

Something I've tried a few times is to dump a long draft blog post into NotebookLM and have the weird fake podcast hosts do an episode about it - I find it useful for checking that the key points I'm trying to make come across, and their interpretation sometimes sparks ideas for clearer explanations