I figured out how to use the ChatGPT mobile app as a custom voice recognition tool including special domain specific words! Just use the prompt below and then copy the requests from the app. It’s way more accurate than the iOS builtin one.
@jeremyphoward
-
University Teaching: Balancing Live and Recorded Learning Experiences
By
–
I've often seen my university colleagues focus on the in-room experience over the recorded experience, and haven't had much luck convincing them to switch their focus. It's tempting to concentrate on the faces you can see live!
-
Recording presentations for wider distribution and engagement
By
–
Given how much time and effort you put into your presentations, it would be great if you could try to get high quality recordings of them and make them publicly available. (I get 100-1000x more people watching my recordings than the live presentations, so that's the key medium)
-

Grok’s limitations in analyzing specific threads
By
–
The most obviously useful thing for @grok to do AFAICT would be to let me ask questions about specific threads. But AFAICT it can't do that 🙁
-

New VSCode Extension Converts HTML to FastHTML Components
By
–
Sweet new vscode/cursor/codespaces extension from @callmephilip — it natively converts HTML tags to FastHTML FT components! It even lets you choose between attrs-1st and children-1st syntax. https://
marketplace.visualstudio.com/items?itemName
=PhilipNuzhnyi.html2ft
… -
Is MLX suitable for model fine-tuning tasks?
By
–
@awnihannun is this something MLX would be good for fine tuning?
-
MLX Fine-tuning and GGUF Conversion on macOS
By
–
Well thank you both! I’d like to document something for folks to follow along with, so what would you recommend for python and macOS? MLX for fine tuning? And I’ll need gguf iiuc?
-
Fine-tuned Models: Python Implementation for MacOS Users
By
–
Sounds interesting! So what would be the easiest way for me to use a fine-tuned model? BTW since it's in Python, maybe it could be made to work in MacOS too?
-
Jeremy Howard frustrated by irrelevant replies and hallucinated answers
By
–
Wow an awful lot of replies, but nearly none actually responding to what I'm looking for… C'mon gang if you don't know, that's fine, but don't hallucinate like you're an LLM! This seems to be the one answer that actually fits the request:
-
Flow speech synthesis tool needs fine-tuning for vowel accuracy
By
–
Flow is what I use now. It's pretty good, but gets my vowel sounds wrong sometimes. I'd love to be able to use a fine tuned model.
