Most people don't know what itβs capable of, how it differs from ChatGPT and what kind of amazing content it can generate. π
8 compelling ways to talk to The New Bing:
π§΅π
1/ Choose the most appropriate parameter:
Creative π more variation and creativity in its output (can be prone to hallucination)
Balanced π Best for table/chart creating
Precise π The most accurate although responses can be short
2/ Always ask Bing to search:
π Research x and then provide y in the style of x
ie. Research Alex Harmozi on Twitter and YouTube (x) and then provide five hypothetical titles on how to sell ice to Eskimos (y) in his style (x)
3/ Another research example:
π Research Dr Andrew Huberman and then provide me with his top recommendations on how to sleep effectively.
(note - be sensible and check quantity recommendations if you want to take supplements)
4/ Use tables/charts for smarter research:
π Review movie databases and provide me with a chart of five movie suggestions about Artificial Intelligence, along with their directors, audience ratings on iMDB and Rotten Tomatoes, and where I can currently watch them.
5/ Provide information in steps:
(Bing's π₯ response in the next tweet)
5 (con't)/ Bing's response:
6/ Decide where to go for lunch:
π Research Google Maps, Bing and Tripadvisor and provide me with a chart of five recommendations for Pad Thai in Sydney. Only include 4.5+ rated restaurants. Label the chart by name, address, rating and phone number.
7/ Create simple SVGs
π Create an SVG of a red apple
8/ Summarise papers:
π Find and read the paper "On the Electrodynamics of Moving Bodies" and summarise it in layman's terms.
An important point:
Bing is not perfect. But itβs awesome. All you need to do is learn how to talk to it. Test different messages and see what works best. Give it a try and let me know what you think.
@OpenAI has released the code for their Consistency Model, a new technique for creating images with AI in one shot.
Allowing AI to create images from natural language in real time.
More below π
Unlike Diffusion, which needs many steps to remove noise from images, this method can generate realistic images in a single step.
They can also perform zero-shot image editing, which means they can modify existing images without any additional training or data. For example, they can change the color or the style of an image.