I’ve been playing around a lot with Ollama, an open source project that allows one to run LLMs locally on their machine. It’s been fun to mess around with. Some benefits: no rate-limits, private (e.g., trying to create a pseudo therapy bot, trying to simulate a foul mouthed smarmy sailor, or trying to generate ridiculous fake news articles about a Florida Man losing a fight to a wheel of cheese), and access to all sorts of models that get released.

I decided to try my hand at creating a simplified interface for interacting with it. The result: Super Simple ChatUI.

As if I need more side projects. So it goes!

Using a customized prompt, you can (for now, at least), get ChatGPT to misbehave a bit.

For example, I turned it into an angry programmer.

Earlier this evening, I was playing around with OpenAI’s GPT-3 language model for generating “human-like text.”

I gave it the following prompt:

Write a plot about a movie that involves rogue unicorns who want to
conquer Earth and the planet’s only hope is an Australian Cattle dog named Benson who sleeps a lot.

The response?

The unicorns, led by their king, Uni, have been planning their conquest of Earth for years. They have been observing the humans and have concluded that they are weak and vulnerable. The unicorns have developed a powerful magic that will allow them to take over the planet.

Benson, an Australian Cattle dog, is the only one who can stop them. Benson is a lazy dog who loves to sleep. He is content to spend his days lounging around and eating food. However, when the unicorns begin their attack, Benson is the only one who can stop them. He rallies the other dogs and leads them in a fight against the unicorns.

The unicorns are powerful, but they are no match for Benson and the other dogs. Benson is able to defeat Uni and the other unicorns, and the Earth is saved.

Summer blockbuster coming soon to a theater near you!