Open Source Self-Improving AI with Vignesh Baskaran

Today we are talking with Vignesh Baskaran, the CTO and co-founder of Hexo Labs, 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.

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(80)

AI and Proactive Reliability with Kolton Andrus

Today we're talking with Kolton Andrus, the Founder and CEO of Gremlin, about what happens to reliability when AI is writing most of the code. Kolton helped build the Chaos Engineering practice of bot...

8 Apr 55min

Making Data Agent Ready with Andre Elizondo

Today we are talking with Andre Elizondo, the Director of Innovation at Mezmo about their open source agentic harness for SREs called AURA. Mezmo got their start handling observability data at scale. ...

27 Mar 51min

Exponential Engineers with Ashmeet Sidana

Today on the show, we have a special guest — Ashmeet Sidana, the founder of Engineering Capital. Ashmeet started his career as an engineer at some great companies like Hewlett-Packard and Silicon Grap...

9 Jan 53min

Powered by Neurons with Ewelina Kurtys

Today we have Dr. Ewelina Kurtys on the show. Ewelina has a background in Neuroscience and is currently working at FinalSpark. FinalSpark is using live Neurons for computations instead of traditiona...

16 Sep 202542min

Lessons from Building AI Agents with Rafal Wilinski

Today we're talking with one of our favorite engineers, Rafal Wilinski. Rafal has been on the cutting edge of AI development in the last few years as he has led AI teams at Zapier and Vendr. Rafal wa...

12 Aug 20251h 8min

Building a High-Ownership Engineering Culture with Matt Watson

If you’ve ever felt like engineering teams are stuck in execution mode—heads down, building what they’re told—then today’s episode is for you. We're talking about what it really takes to build high ow...

5 Aug 202551min

Building CI for the age of AI Agents with Aayush Shah

Today's episode is with Aayush Shah. Aayush is one of the co-founders of Blacksmith, which is a CI compute platform. Basically, Blacksmith will run your GitHub Actions jobs faster and with more visibi...

22 Jul 20251h 4min