"Role prompting"... telling the model to assume a role has never been a good way to elicit capabilities/style/etc.
For instance, if you ask one of the Claude models to simulate Bing Sydney, assuming you can get it to consent, the simulation will probably be very inaccurate. But if you use a prompt that tricks them into... See more
GPU-accelerated databases are mind-blowing!
Imagine a database natively integrated with best-in-class AI foundational models:
• Zero warmup latency
• Massive GPU-backed scalability
• Ability to process your data with any model
• Ability to train... See more
📢 Just released: The latest report on the fourth wave of #OpenData!
Discover the diverse scenarios for open data and generative AI in this insightful study by @sverhulst and Hannah Chafetz from @TheGovLab.
Learn more here 👉 https://t.co/wvpQrU1WH4 https://t.co/p5dFN6mEVo
One line, one word. ✏️🔤 A simple #p5js sketch where you draw a line and Gemini tries to describe it in a single word. I find it really fun to have the model write on the canvas with me (wherever drawing finishes). Uses Gemini 1.5 Flash API. Try it + fork/remix my sketch here: https://t.co/Ks5qsmYNH6
I wanted to see if AI could code me a complex app.
Not a crappy little one-off script. A real program.
Just one little problem: I mostly suck at coding.
So can AI make magic for someone like me?
Yeah. But...it's... See more
navigating the latent space of colors 🌈✨
do LLMs “see” colors differently from humans?
we perceive colors through wavelengths while LLMs rely on semantic relationships between words. to explore this, i mapped two color spaces: https://t.co/JSHCFjYu61