- Prompt Hunt Newsletter
- Posts
- Rewind Your Digital Life
Rewind Your Digital Life
Here's your daily briefing:
Everything in this 3-part thread from Sundar Pichai is 🤯🤯🤯 but especially this first tweet showing the increasingly impressive, exciting, and slightly terrifying development of text-to-video generative AI:
1/ From today's AI@ event: we announced our Imagen text-to-image model is coming soon to AI Test Kitchen. And for the 1st time, we shared an AI-generated super-resolution video using Phenaki to generate long, coherent videos from text prompts and Imagen Video to increase quality.
— Sundar Pichai (@sundarpichai)
6:21 PM • Nov 2, 2022
DreamBooth is becoming popular for creating custom Stable Diffusion models using your images.
Here is a beginner friendly thread on how it works: 🧵
— Divam Gupta (@divamgupta)
2:30 PM • Nov 1, 2022
And if you're not a fan of the tweet thread format, check out this essay which also goes into more detail about how to use these tools yourself:
And in that vein, here's yet another tool to imagine yourself in different styles, hairstyles that is:
Another educational thread, this one about GPT-3 and some commonly used but probably less commonly understood terms:
What is "Zero-Shot", "One-Shot", "Few-Shot", and "Fine-Tuning" in the context of @OpenAI#gpt3?
From the #gpt3 paper
arxiv.org/pdf/2005.14165…These terms refer to how many examples a language model needs to perform a task
— Brian Sunter 🧠(@Bsunter)
12:16 AM • Nov 1, 2022
This thread by Dan Siroker about his new (Andreesen Horowitz-backed) project, Rewind AI, has us really excited. This just feels like something that should exist, so we're glad that it finally does. How many times have you accidentally closed a tab that you only vaguely remember and wasted hours trying to find it? Or is that just us?
Today we are launching Rewind: the search engine for your life rewind.ai
It’s a macOS app that enables you to find anything you’ve seen, said, or heard.
We’re also announcing that we’ve raised $10m at a $75m valuation led by Andreessen Horowitz.
(1/23)
— Dan Siroker (@dsiroker)
12:04 PM • Nov 1, 2022
And for the video version:
Today in "things we don't understand but can tell are a really big deal":
Incredible!
Meta AI releases a database of more than 600+ million metagenomic structures—the least understood proteins on earth. Language models and API released for researchers.
Explore here: esmatlas.com
— elvis (@omarsar0)
2:11 PM • Nov 2, 2022
This is very cool visualization map via Nomic of how people use Stable Diffusion:
We've just released from @nomic_ai a new map for exploring 6+ million AI-generated images and the prompts used to created them, collected by @krea_ai. atlas.nomic.ai/map/809ef16a-5… The most exciting thing for me here is how this changes full-text search: here's why (thread).
— Ben Schmidt / @[email protected] (@benmschmidt)
4:40 PM • Nov 2, 2022
That's it for today...we'll see you tomorrow!

"a realistic photograph of an old man looking into a computer with a picture of him as a child on the screen" 🤣


