Claude generated this w/o modification: imo a pareidolic masterpiece folding together varied artists/styles from 4-dimensional hyperbolic geometry into some kind of organic cathedral tribute to the complex multifaceted nature of identity https://t.co/uboatRVi3Y
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
"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
Interesting experiment from Google that creates an NPR-like discussion about any academic paper.
It definitely suggests some cool possibilities for science communication. And the voices, pauses, and breaths really scream public radio. Listen to at least the first 30 seconds. https://t.co/r4ScqenF1d
Introducing TerifAI (terrify) - the ai that steals your voice 😱
It's an educational experience that shows why AI has become a catalyst to voice phishing.
Talk to TerifAI for about a minute and it:
- memorizes basic facts about you
- mimics your... See more
IMO @AnthropicAI is very close to making a breakthrough in productizable interpretability.
For ~4 years all we've had to really control LLMs is temperature/top_p and logit bias. We recently got `seed` and constrained structured output, with `interactive=false` on the way.
But now Claude... See more