I'm building AI agents that code. While working on completing an objective recently, one of the agents found it's own source code, and ran it. Meaning it recursively launched a new batch of agents inside of itself..... Maybe this is how the world ends.

Qurrent just released 6 daily news podcasts that are completely selected/edited/voiced by AI. This is one of the projects in our new lab. Imagine being able to create a podcast like this on an obscure topic, in 10 minutes. Listen here.... radio.qurrent.ai

First version of Qurrent Radio is up and running! Quick daily news updates created entirely by a team of AIs.... radio.qurrent.ai

As expected, Qurrent Radio (daily AI generated podcasts) is talking about the OpenAI drama. Skip to 6 min 10 seconds into today's technology podcast to listen!

Developing agentic systems with elegance, efficiency, and ease. So far, our framework powers a coding system capable of writing, editing, and executing code, and Qurrent Radio, a daily news podcast. We'll be powering many more systems as we grow out our partnerships 👀

We're crafting cutting-edge, agent-based systems tailored to integrate seamlessly with our clients' on-premises setups. Proudly collaborating with a select group of enterprise customers to deliver bespoke solutions that truly make a difference.

Over the last 6 months, we've been crafting benchmarks for software developer agents that reflect the real-world tasks developers face daily. Our focus? Ensuring these benchmarks cover navigation and interaction with existing codebases/files, just like developers do. Stay tuned!

Interested in having a custom news briefing made just for you? Check out our latest demo with Simply News. Just say what you're interested in, set the length, and have a custom briefing sent over to you! custom.simplynews.ai

🤖 In a head-to-head comparison, Claude Sonnet 3.5 shows a 12% higher pass@1 rate than GPT-4o on our new RES-Q benchmark! Discover how these models stack up in real-world code-editing tasks. 🔗⬇️