Episodes

Four years of tape. Every episode is checked claim by claim and playable.

283episodes processed
276hours of tape
5,957statements extracted → 1,046verdicts →
2026792025129202464202311

11 episodes in 2023

🎙LATENT SPACE
1h 33m
latent-space Dec 17, 2023
The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
Sourcegraph's Beyang Liu and Steve Yegge discuss the General Availability of Cody and explain the 'Normsky' architecture, which synthesizes deterministic code graph indexing with statistical…
20 statements 7 featured 2 assessments 1 contradicted
🎙LATENT SPACE
1h 7m
latent-space Dec 5, 2023
The State of Silicon and the GPU Poors - with Dylan Patel of SemiAnalysis
Dylan Patel, Chief Analyst at SemiAnalysis, joins the Latent Space Podcast to examine the economics, physical bottlenecks, supply chain geopolitics, and silicon architecture underpinning mod…
34 statements 14 featured 17 assessments 3 contradicted
🎙LATENT SPACE
1h 18m
latent-space Nov 3, 2023
Beating GPT-4 with Open Source Models - with Michael Royzen of Phind
In this interview, Phind founder Michael Royzen discusses his journey from building on-device computer vision apps to creating an industry-leading AI developer search engine. He details how …
24 statements 10 featured 8 assessments
🎙LATENT SPACE
43m
latent-space Oct 27, 2023
Powering your Copilot for Data - with Artem Keydunov from Cube.dev
Cube co-founder Artem Keydunov joins hosts Swix and Alessio Fanelli to discuss how semantic layers bridge the gap between large language models and tabular databases. He details the technica…
10 statements 3 featured
🎙LATENT SPACE
1h 12m
latent-space Oct 21, 2023
Why AI Agents Don't Work (yet) - with Kanjun Qiu of Imbue
Imbue CEO Kanjun Qiu examines why current autonomous AI agents encounter severe reliability bottlenecks, detailing how foundation models optimized for explicit natural language reasoning, sy…
20 statements 7 featured 2 assessments
🎙LATENT SPACE
1h 24m
latent-space Oct 20, 2023
The End of Finetuning — with Jeremy Howard of Fast.ai
Fast.ai co-founder Jeremy Howard discusses the evolution of deep learning, arguing that traditional fine-tuning must be replaced by continued pre-training while passionately advocating for o…
25 statements 10 featured 5 assessments
🎙LATENT SPACE
1h 13m
latent-space Oct 12, 2023
RAG is a hack - with Jerry Liu of LlamaIndex
In this episode of the Latent Space podcast, LlamaIndex creator Jerry Liu discusses the origins, architecture, and evolution of LlamaIndex, breaks down the technical trade-offs between RAG a…
14 statements 3 featured 1 assessments
🎙LATENT SPACE
1h 28m
latent-space Sep 20, 2023
Generating your AI Media Empire - with Youssef Rizk of Wondercraft.ai
In this episode of the Latent Space podcast, Wondercraft AI co-founder Youssef Rizk joins Shawn 'Swix' Wang to discuss building an AI-powered audio studio, evaluating startup pivots, archite…
24 statements 8 featured 1 assessments
🎙LATENT SPACE
1h 56m
latent-space Aug 31, 2023
RWKV: Reinventing RNNs for the Transformer Era
In this extensive discussion, UIlicious CTO Eugene Cheah details the architecture, grassroots open-source origins, and multilingual capabilities of RWKV, demonstrating how linear-time RNNs c…
30 statements 10 featured 13 assessments 1 contradicted
🎙LATENT SPACE
1h 4m
latent-space Aug 3, 2023
FlashAttention-2: Making Transformers 800% faster AND exact
In this technical interview, researcher Tri Dao discusses the architectural principles behind FlashAttention and FlashAttention-2, highlighting how memory-aware algorithmic design, hardware-…
17 statements 5 featured 4 assessments
🎙LATENT SPACE
1h 23m
latent-space Jun 20, 2023
Ep 18: Petaflops to the People — with George Hotz of tinycorp
In this interview on the Latent Space podcast, George Hotz details the founding theses of tinycorp, the minimalist architecture of the Tinygrad framework, the engineering behind the Tinybox …
32 statements 7 featured 9 assessments 2 contradicted
2024 →
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.