Emmanuel Ameisen, an interpretability researcher at Anthropic, joins the podcast to demystify how large language models work. Subscribe to the Gradient Flow Newsletter 馃摡 https://gradientflow.substack.com/ Subscribe: Apple 路 Spotify 路 Overcast 路 Pocket Casts 路 AntennaPod 路 Podcast Addict 路 Amazon 路 RSS. Detailed show notes - with links to many references - can be found on The Data Exchange web site.
All content for The Data Exchange with Ben Lorica is the property of Ben Lorica and is served directly from their servers
with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.
Emmanuel Ameisen, an interpretability researcher at Anthropic, joins the podcast to demystify how large language models work. Subscribe to the Gradient Flow Newsletter 馃摡 https://gradientflow.substack.com/ Subscribe: Apple 路 Spotify 路 Overcast 路 Pocket Casts 路 AntennaPod 路 Podcast Addict 路 Amazon 路 RSS. Detailed show notes - with links to many references - can be found on The Data Exchange web site.
Why Digital Work is the Perfect Training Ground for AI Agents
The Data Exchange with Ben Lorica
42 minutes
2 months ago
Why Digital Work is the Perfect Training Ground for AI Agents
Andrew Rabinovich, CTO and Head of AI at Upwork, discusses how digital work marketplaces serve as ideal testing grounds for AI agents, exploring their custom reinforcement learning approach called RLEF (Reinforcement Learning from Experience). Subscribe to the Gradient Flow Newsletter 馃摡 https://gradientflow.substack.com/ Subscribe: Apple 路 Spotify 路 Overcast 路 Pocket Casts 路 AntennaPod 路 Podcast Addict 路 Amazon 路 RSS. Detailed show notes - with links to many references - ca...
The Data Exchange with Ben Lorica
Emmanuel Ameisen, an interpretability researcher at Anthropic, joins the podcast to demystify how large language models work. Subscribe to the Gradient Flow Newsletter 馃摡 https://gradientflow.substack.com/ Subscribe: Apple 路 Spotify 路 Overcast 路 Pocket Casts 路 AntennaPod 路 Podcast Addict 路 Amazon 路 RSS. Detailed show notes - with links to many references - can be found on The Data Exchange web site.
