I’ve had a number of generative AI projects floating in the back of my mind that require a verbal interface - a way to communicate with a model using speech. While this has definitely been a capability of models for a while now, the process is a bit janky; generally you’d go from audio to text, and then send the text to a generative AI model, and then receive text in return, and then emulate audio using that text. With OpenAI’s recently released Realtime API, we can skip a few of these steps and make a true conversational AI!

A tool I find myself using more and more over the last year is called Locust, which is a python application geared at load testing websites. With a few simple commands you can create a repeatable test that you can scale at will, up to thousands of emulated users, and with lots of pathing and configuration options to meet your needs!

Continuing from our post the other day about prompt terminology, I’d like to focus on specific techniques that can be used to write prompts that get the results you’re looking for from Generative AIs. This is a user-friendly summary of the research paper available here, based on a presentation I’m giving at my workplace.

Driven by a report that education and training is one of the major drivers behind organizations using AI, and inspired by a paper on various prompting techniques, I’m working on a presentation for my workplace about the various ways you can prompt a generative text AI to ensure you get the content you’re looking for. Here’s a preview!

Piggybacking on some of the stuff we talked about in Multi-Agent Interactions, I’ve been able to use generative AI to ask a series of questions that it generates itself to meet multi-element criteria. Which is just a fancy way of saying “keep talking until you have the info we’re looking for”. I’ll show you how it works with my Mythic AI Game Master and talk about some uses at work as well.