Description
Goodfire is an AI interpretability research lab focused on understanding and intentionally designing advanced AI systems. We had CTO and co-founder Dan Balsam come and join us to talk about what they're building, why and how.
• Introducing Goodfire
• Introducing the problem space they are in and the mission at hand.
• The engineering mentality that sparked Goodfire to life in late 2022.
• What is a research lab?
• Dan walks us through Silico and really breaks down for us the what, the why, the how.
• What is AI Safety + AI Alignment?
o An emphasis inside Goodfire is AI alignment via interprability; what does this mean and how are you building towards AI alignment?
o AI Safety is a pretty big umbrella; Dan breaks down why we need great engineers? Understanding how do great engineers step into AI safety research and be effective.
• Engineering challenges:
o Supporting model frontier level infrastructure
o long horizon agents; creating the right scaffolding and harnesses.
• Future bets being placed on Goodfire/AI generally Hiring
If you're keen to share your story, please reach out to us!
Guest: https://www.linkedin.com/in/dbalsam/
Powered by Artifeks!
https://www.linkedin.com/company/artifeksrecruitment
https://www.linkedin.com/in/agilerecruiter
LinkedIn: https://www.linkedin.com/company/enginearsio
Twitter: https://x.com/Enginearsio
All Podcast Platforms: https://smartlink.ausha.co/enginears
Hosted on Ausha. See ausha.co/privacy-policy for more information.
