Public evidence record
Published podcast speaker
Books, apps, and tools
app / uses
“It runs Whisper, and you can do things like you can paste in the URL to a YouTube video and it'll pull the audio and give you a transcript. So, that's how I watch YouTube now, is I slap it into Mac Whisper, and then I hit copy and paste into Claude, and then I use the Claude web app to do things.”
app / uses
“It runs Whisper, and you can do things like you can paste in the URL to a YouTube video and it'll pull the audio and give you a transcript. So, that's how I watch YouTube now, is I slap it into Mac Whisper, and then I hit copy and paste into Claude, and then I use the Claude web app to do things.”
Claim ledger
9 transcript-backed records
01 / preference
“It runs Whisper, and you can do things like you can paste in the URL to a YouTube video and it'll pull the audio and give you a transcript. So, that's how I watch YouTube now, is I slap it into Mac Whisper, and then I hit copy and paste into Claude, and then I use the Claude web app to do things.”
02 / preference
“This is where I've been pushing the definition. I love the term slop. Where I've been pushing the definition of slop as AI generated [00:41:00] content that is both unrequested and unreviewed and the unreviewed thing is really important like that's the thing that elevates something from slop to not slop is if A human being has reviewed it and said, you know what, this is actually worth other people's time.”
03 / preference
“for running prompts through them. And then When you look at the, the really, the top tier model providers right now, I think, are OpenAI, Anthropic, Google, and Meta.”
04 / preference
“Currently, I run them through Whisper and then I do the transcript that way, but being able to do the multimodal thing with those would be really useful.”
05 / preference
“That's cool, because I've been using Google Gemini's bounding block stuff recently, it's very, very impressive.”
06 / preference
“Like, I want to control when I'm using the gold model versus when I'm not, which I can do because I created myself a custom GPT that does what I need.”
07 / preference
“I don't want to spend five or 10 minutes tediously debugging my way through it, through a, a nested list algorithm, but I'm happy for code interpreter to, to go ahead and do that. And in fact, when it wrote the code, I watched it make the exact same mistakes I would've made, like forgetting, getting off one off by one errors and all that kind of thing.”
08 / preference
“Because I want to run this thing, but I want to control the container and I want to give it network access, all of that kind of stuff.”
09 / preference
“Like Vicuna 13 b i i, I, I think is the current best available open mo model that I've played with.”