PodcastIntel
Sign in Get Started Free
Latent Space: The AI Engineer Podcast

Latent Space: The AI Engineer Podcast

Alessio Fanelli · Technology · EN

This podcast explores the technical infrastructure, models, and agents used by leading AI labs, with a focus on AI for science. It features in-depth discussions with prominent AI engineers and researchers. The show is geared towards individuals interested in the practical engineering aspects of...

198
Episodes
89
Guests

Episodes (Page 3)

Nov 10, 2025 · 35m
Jared Palmer (SVP GitHub, VP CoreAI Microsoft) launched Agent HQ, new collaboration hub for coding agents and developers after success with v0 coding agent at Vercel
Jared Palmer
35m
Nov 10, 2025 · 43m
Jed Borovik (Google Labs) building Jules, ambitious coding agent running on Google infrastructure, managing 2M token context windows with developers using agent for hours/days
Jed Borovik
43m
Nov 6, 2025 · 53m
Priscilla Chan and Mark Zuckerberg (Biohub founders) specialized from broad CZI philanthropy toward frontier AI + biology research with focus on building virtual cell models and virtual immune systems
Mark Zuckerberg Priscilla Chan
53m
Oct 31, 2025 · 42m
Malte Ubl (Vercel CTO) introduced Workflow Development Kit bringing durable execution to serverless functions, enabling agents to pause, resume, and wait indefinitely without cost
42m
Oct 30, 2025 · 1h 37m
Emily Glassberg Sands (Head of Data & AI, Stripe) oversees payments infrastructure powering $1.4T annual transaction volume (~1.3% global GDP), creating massive AI optimization opportunity
Emily Glassberg Sands
1h 37m
Oct 16, 2025 · 1h 8m
OpenPipe pivoted from distilling GPT-4 into cheaper models to RL-based agent training as frontier model prices dropped, addressing why 90% of AI projects fail due to reliability rather than capabil...
Kyle Corbitt
1h 8m
Oct 7, 2025 · 45m
OpenAI launched AgentKit enabling developers to build, deploy, and optimize AI agents with visual Agent Builder allowing customer support agent creation in 8 minutes and live deployment within ChatGPT
Christina Huang Sherwin Wu
45m
Oct 2, 2025 · 1h 1m
Dylan Field (Figma CEO) explains how Figma Make enables designers to build with AI, positioning design as ultimate moat in 'vibe coding' era
Dylan Field
1h 1m
Sep 25, 2025 · 1h 20m
Sourcegraph's Amp Code achieves 15 shipping cycles per day with no code reviews through effective dogfooding and best-in-class coding agent architecture, rejecting subagents and prompt optimizers a...
Quinn Slack Thorsten Ball
1h 20m
Sep 11, 2025 · 57m
Context engineering moves beyond simple RAG by addressing context rot, retrieval quality, chunking strategies, and memory structuring
Lance Martin
57m
Sep 5, 2025 · 1h 1m
Gorkem and Batuhan from Fal.ai (raised $125M Series C, crossed $100M ARR) discuss technical history of generative media and model impact on inference
1h 1m
Aug 29, 2025 · 1h 18m
Ari Morcos (Datology) argues data curation is most impactful and underinvested area in AI, with effective filtering, rebalancing, sequencing, and synthetic generation outweighing architecture focus
Ari Morcos
1h 18m
Aug 19, 2025 · 57m
Modern vector databases differ fundamentally from information retrieval systems; Chroma prioritizes context quality and preventing 'context rot' as systems grow rather than just adding more embeddings
Jeff Huber
57m
Aug 15, 2025 · 1h 8m
OpenAI continues scaling RL for reasoning, moving beyond offline learning with online interactions and sample-efficient human curation; wall-clock time limitations in training remain an engineering...
1h 8m
Jul 31, 2025 · 1h 18m
Nathan Lambert discusses evolution from RLHF to RLVR (Reinforcement Learning with Verifiable Rewards) in Tulu 3 paper for tasks with clear success criteria
1h 18m
Jul 23, 2025 · 56m
ChatGPT processes 2.5B prompts daily and will match Google's search volume by end of 2026; AI agents require structured, queryable data unlike human browsing patterns, creating new AI SEO/GEO industry
56m
Jul 16, 2025 · 1h 15m
Cline pioneered plan+act paradigm for coding agents as alternative to fast-apply models; operates as VS Code extension rather than fork to provide transparency and avoid vendor lock-in
Saoud Rizwan
1h 15m
Jul 11, 2025 · 1h 4m
Speak represents third-generation language learning software (after Rosetta Stone Gen 1 and Duolingo Gen 2) by leveraging speech and language models to provide adaptive, fluent instruction previous...
Andrew Hsu
1h 4m
Jul 9, 2025 · 49m
Video diffusion models evolved from simple frame extension to sophisticated systems; Google's Veo 3 dominates 2024 by adding native audio generation, eliminating need for separate lipsynching and S...
49m
Jul 2, 2025 · 1h 18m
Jack Morris focuses on information-theoretic understanding of LLMs including embeddings and latent space representations, offering underrated research with accessible explanations for mass audience
Jack Morris
1h 18m

Track New Episodes & Guest Appearances

Subscribe to get AI-powered episode summaries, guest detection, and weekly email digests.

Sign Up Free →