Hello friends, and welcome to the 167 new humans joining us since yesterday.

Grab a seat, and a plate and let's dig in!

Prompt: List the topics in today’s email:

🌅 Addressing climate change🎥 Seamless video from an image🦾 Robots writing code📝 AI in Notion

🫦 BEN'S BITES

This may be one of the best generative tools I’ve seen. Generate images and videos with AI, StableBoost.^531† Not only does it produce several variations, but you can add modifiers super easily, and it learns your preferences. Andrej Kaparthy gave his praises¹⁶⁶ for it and looks like he may be advising Tal.

Google hosted an AI announcements¹¹² conference thingy called AI@. Here are the three things you need to know:1. Supporting 1,000 languages with AI. 1,000 Languages Initiative, is an ambitious commitment to build an AI model that will support the 1,000 most spoken languages.2. Empowering creators and artists with AI. By bringing its text-to-image generation technologies to AI Test Kitchen, which provides a way for people to learn and experience it. Read about it here¹⁵².3. Addressing climate change and health challenges with AI. Flood Forecasting. Google uses satellite imagery and AI to accurately map rivers, and model what areas will be flooded, which you can view here¹⁵⁶. Wildfire detection system. Google trained ML models to use satellite imagery to identify and track wildfires in real time and predict how they will evolve to support first responders. Watch the video here¹²⁴. Low-cost AI ultrasound device that can determine critical details of a pregnancy and detect issues early. Unlocking eye screening for anyone with a smartphone camera. They are evolving this technology to work with a photo of an eye taken on a consumer camera. (read the full blog post here¹¹⁹)

Google also explored whether Robots could write their own code¹⁵⁸.

Unlimited conversation¹⁹⁹ by my wife; an AI-generated, never-ending discussion between Werner Herzog and Slavoj Žižek.

👋 Too many links?! I created a database for all links mentioned in these emails. Refer 1 friend using this link and I'll send over the link database.

Improved text-to-image synthesis, style transfer, and painting with word capabilities - eDiffi¹⁸⁶.

Contrastive decoding is a more reliable search objective¹⁰⁴ by contrasting LMs of different sizes.

A new model to aid in trying on clothes… current solutions only let us try on 1 garment at a time but this model proposes a way to try on multiple layers of garments²⁰³. Try on that Tee, with that sweatshirt and throw the coat on top too.

The recent trend of open-source AI collaboration between China and the US^119†. The key takeaways are; the trend is being driven by a desire for greater AI innovation, it’s also being driven by a desire to avoid the risks of AI development and it could lead to greater cooperation between the two countries on AI development. However, it could lead to greater competition between the two countries on AI development and the US losing its competitive advantage.

You can now generate seamless video from still images with just one click³¹⁰ - this is insane!!! Runway’s Frame Interpolation.

Coqui is aiming to combine a bunch of generative AI tools²¹³ together in their platform.

Another AI avatar platform to add to our lists - “Portrait” by Vana³⁶¹ is a generative art studio that can create self-portraits of you in infinite styles. Packy McCormick is a fan.¹¹²

We’ve all seen that woman in website customers, right? She apparently uses a lot of software! Well instead of using her face, why not use an ultra-realistic AI-generated face^282†?

OpenAI opens its first accelerator¹³⁶ - it will give roughly 10 AI startups $1M each and early access to its systems. I wonder if Ben’s Bites counts as an ‘AI startup’ 🤔, what could we do with $1M 👀.

Do you know that all of these recent DreamBooth and Stable Diffusion apps (avatars etc) are all using one API¹⁸⁰? Astria was actually mentioned previously and they provide the API that powers these apps.

Notion lover? Then you’ll enjoy this AI writer in Notion³²⁴.

A cool new tool that lets you animate two Stable Diffusion images¹⁶⁸ together.

AI short film¹⁸⁸ created with text-to-video.

🖼 AI IMAGES OF THE DAY

Bob Ross burying another corpse at a location he will paint later

👋 SEE YA