Today we are talking with Vignesh Baskaran, the CTO and co-founder of @hexoai, about teaching AI agents to improve themselves. Vignesh has been training neural networks since 2012, back when he was still called a data scientist. Then he became an ML engineer and now an AI engineer, though he says the underlying work has never really changed. It's to figure out how to make a system behave the way you intend it to. He built the litigation search engine that Google itself became a customer of, and now he's chasing something new, agents that rewrite and retrain other agents without a human in the loop. We dig into Sia, the meta-agent at the center of Hexo's research, and why improving an agent means touching both its harness and its actual model weights, not just one or the other. We talk about proxy evals for when you don't have much to ground truth. The Darwin-Gödel machine and why formal verification is too strict a bar for anything commercial. How Hexo's work echoes DeepMind's Alpha lineage from AlphaGo to AlphaEvolve, and the spectrum from clearly verifiable to totally subjective tasks? Why VAE evals are quietly wrecking agent quality across the industry, and a great story about an agent that discovered a customer's own eval file was silently corrupted, something buried in hundreds of thousands of traces that no human would have caught. Watch on YouTube: youtu.be/SEYmUH_Ae3U @tweetvbaskaran

DARPA Lift Challenge — T–15 Days darpa.mil/research/challenge…

We are hiring part time podcast hosts for Software Huddle. Please reach out to [email protected] if you are interested.

Glauber from @tursodatabase talks about his AI stack✨ @glcst

➡️@valkey_io is the new Redis.

Catherine Jue talks about 3 things her team at @usekernel looks for in new hires. Visit kernel.sh to check out how Kernel is building Open Source infra for AI Agents.

AI and Proactive Reliability with Kolton Andrus Today we're talking with Kolton Andrus, the Founder and CEO of @GremlinInc, about what happens to reliability when AI is writing most of the code. Kolton helped build the Chaos Engineering practice of both Amazon and Netflix before starting Gremlin. In our conversation we talk about scar tissue, the intuition engineers develop from being woken up at 3:00 AM to fix production outages, and how AI doesn't have any of it. It generates code in an afternoon that maybe took a team previously weeks to build, but none of those painful lessons come along for the ride. We dig into why 10x more code might mean 10x more failures. The concept of reliability guardrails, think ethical guardrails, but for keeping your systems up. Why you still have to test in production no matter how good your staging environment is? How Gremlin is rethinking their product for the world where agents, not engineers, are essentially the primary users. And why we're entering a painful, narrow part of the hourglass before AI gets good enough to handle all of this on its own. Watch On YouTube: youtube.com/watch?v=Gbm8gaoO… @KoltonAndrus | @seanfalconer | @alexbdebrie

Making Data Agent Ready with Andre Elizondo Today we are talking with Andre Elizondo, the Head of Innovation at @mezmodata about their open source agentic harness for SREs called AURA. Mezmo got their start handling observability data at scale. Logs, traces, metrics, the usual stuff. AURA is their answer to a growing problem, as system complexity outpaces humans' ability to make sense of all that data, how do you actually make it actionable for AI agents? We get into their approach to context engineering, essentially making data agent ready before it hits the model. Why they built their own orchestrator in Rust? How they handle memory and self-correction in agent loops? Their take on MCP and where it fits versus Skills and code sandboxing and how the SRE role is evolving as agents become trusted teammates. Watch on YouTube: youtu.be/vr6OA8ietsc @seanfalconer | @alexbdebrie