soon own model but not with dreambooth
AI
-
App Store minimum requirements: webview and in-app payments
By
–
Anyone know what MINIMUM functionality I need over just the webview to get accepted into app store? I guess I need in-app payment too right?
-
Developer Launches iOS App for AI-Powered Interior Design
By
–
✅ Installed Xcode finally and started making an iOS app for https://t.co/JWfbxSX1ou
— @levelsio (@levelsio) 2 janvier 2023
Just a webview now but will add more functionality! pic.twitter.com/HQz2QOyspcInstalled Xcode finally and started making an iOS app for http://
interiorAI.com Just a webview now but will add more functionality! -
AI Chatbot Generates Python Code for UMAP Visualization of Handwritten Digits
By
–
Using Poe Sage (GPT-3.5 chatbot from @Quora
) to ask a fast-talkin' wise guy from a 1940s gangster movie how to use UMAP to visualize the topological manifold of UCI ML handwritten digits. "Snazzy" Python code and Matplotlib plot shown in reply. https://
poe.quora.com/s/kjbVTU3hH7mL
b82H1L6S
… -
Airlines Need Cloud Tech Overhaul for Real-Time Data Integration
By
–
The #Southwest meltdown shows #airlines are overdue for a massive tech overhaul that would take advantage of highly scalable #cloud systems and fully connect disparate sources of real-time #data
@bellelin_
@alyrose
#CIO
@gurobi
-
Samsung Launches Voice Assistant Rival to Apple Siri
By
–
Samsung copying Siri, basically. I’d say it is slightly better if you live in Asia.
-
Apple Camera Quality Disappointment Among Users
By
–
You did see how many people were disappointed with the low quality Apple cam?
-
Apple Studio camera criticized for poor quality
By
–
I love the mockery; Apple’s camera on the Studio is shit and they deserve to be called out.
-
Discussion on GPT-3 Tokenization and Spacing
By
–
Just search “GPT-3 tokenization”. It hasn’t changed since GPT-2 days, I don’t think. I just used dashes because you need spaces to be spaces between words.
-
LLM Tokenization: Not Vectors or Letters, but Token Sequences
By
–
It doesn’t see words as embedded vectors or as letters, it sees them as token sequences — chunks of about 4 letters from a fixed mapping of strings to tokens. It does better on letter-based tasks if you ask it to first rewrite words l-i-k-e t-h-i-s.