Sveriges mest populära poddar
Latent Space: The AI Engineer Podcast
Latent Space: The AI Engineer Podcast

The Utility of Interpretability — Emmanuel Amiesen

1 tim 53 min•6 juni 2025
Logga in för att spara

Om avsnittet

Emmanuel Amiesen is lead author of “Circuit Tracing: Revealing Computational Graphs in Language Models” (https://transformer-circuits.pub/2025/attribution-graphs/methods.html), which is part of a duo of MechInterp papers that Anthropic published in Mar...

Full show notes and links

Fler avsnitt

Visa alla avsnitt av Latent Space: The AI Engineer Podcast

Designing for Agents — Zeno Rocha, Resend

1 tim 26 min

What Frontier Labs Buy: A Data Deep Dive with Handshake AI — Garrett Lord & Team

2 tim 44 min

[One Million AI Engineer Special] How Stanford Teaches AI-Native Engineering — Mihail Eric, Monaco

2 tim 1 min

Deep Dive: Anthropic S-1 Myths and Mythos — Jamin Ball, Altimeter

1 tim 42 min

Controlling Biology - Fabian Theis, Helmholtz Munich

51 min

⚡ Behind Latent Space: A Rare Look Inside the Pod | AIEi Shanghai

1 tim 12 min

⚡️ The 2026 Software Factory Standard — Zach Lloyd, Warp.dev

35 min

Building Legal Agents When You Can't See the Data - Jacob Lauritzen, CTO of Legora

1 tim 7 min

Using Agents for Long-Horizon Financial Work — Aman Singh, Arca

26 min

⚡ Building ChatGPT for Finance — Joseph Kim, OpenAI's Head of Financial Services

28 min

Latent Space: The AI Engineer Podcast med Latent.Space finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.