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 9)

Oct 14, 2023 · 1h 5m
Kanjun Qiu of Imbue (recently valued at $1B+) explains why current AI agents fail: they lack consistent reasoning, tool use reliability, and ability to handle complex multi-step tasks
1h 5m
Oct 8, 2023 · 1h 29m
Swyx discusses the AI Horcrux concept and cognitive science approaches to AI engineering, bridging software engineering and foundational AI research perspectives
1h 29m
Oct 7, 2023 · 38m
Swyx outlines Software 3.0 landscape: shift from traditional code to AI-native development, requiring new tools, architectures, and engineering practices
38m
Oct 5, 2023 · 1h 8m
Jerry Liu of LlamaIndex discusses RAG (Retrieval Augmented Generation) as a pragmatic hack addressing context window limitations of early GPT-3 for large datasets
1h 8m
Sep 29, 2023 · 1h 21m
Raza Habib of Humanloop addresses the rite of passage for AI engineers: transitioning from demo to production requires prompt versioning, evaluation, monitoring, and finetuning infrastructure
1h 21m
Sep 20, 2023 · 52m
Youssef Rizk's Wondercraft.ai builds AI-first podcasting startup, producing HN Recap podcast
52m
Sep 14, 2023 · 1h 29m
Chris Lattner of Modular announced $100M Series A for Mojo language and modular AI infrastructure, addressing fragmentation and poor software quality in AI development
1h 29m
Sep 6, 2023 · 1h 0m
Harrison Chase of LangChain discusses the rapid evolution from 2022 startup to $20-25M Series A, expanding from prompt templating to comprehensive LLM orchestration framework
1h 0m
Aug 30, 2023 · 1h 12m
Eugene Cheah discusses RWKV (Receptance Weighted Key Value) models as significant Transformer alternative, reviving RNNs for GPT-class LLMs with better scaling properties
1h 12m
Aug 22, 2023 · 59m
Aman Sanger of Anysphere created Cursor, an AI-first code editor designed to increase AI-assisted coding beyond Copilot's current 46% of VS Code usage toward 90%+
59m
Aug 16, 2023 · 50m
Quentin Anthony of Eleuther AI demystifies the tacit knowledge around training LLMs efficiently, enabling non-insiders to estimate scaling laws and cost-performance tradeoffs
50m
Aug 10, 2023 · 52m
Tianqi Chen of CMU/OctoML discusses MLC (Machine Learning Compilation) enabling LLMs to run on consumer hardware without GPUs
52m
Aug 4, 2023 · 59m
NLW and hosts discuss Code Interpreter release as potential GPT-4.5, highlighting unexpected capabilities beyond coding and challenges in AI model evaluation
59m
Jul 26, 2023 · 54m
Tri Dao explains FlashAttention: I/O-aware optimization reducing attention memory from O(N²) to sub-quadratic O(N) while maintaining exact computation without approximation
54m
Jul 19, 2023 · 1h 19m
Llama 2 released for commercial use with 2 trillion tokens pretraining, 2x context length, and ~$20M RLHF investment, immediately becoming leading open LLM
Anton Troynikov Matt Bornstein Nathan Lambert Russell Kaplan
1h 19m
Jul 17, 2023 · 1h 0m
GPT-3 trained on ~600GB of data (Wikipedia, Books, WebText, CommonCrawl), not the entire internet as commonly claimed
1h 0m
Jul 10, 2023 · 2h 3m
Code Interpreter launched with ability to execute Python code, upload files, and handle edge cases with dependencies like Tesseract and TensorFlow
Alex Graveley Alex Volkov Aravind Srinivas Simon Willison
2h 3m
Jul 2, 2023 · 1h 0m
Data Dan Whitenack from Practical AI discusses 5-year podcast journey covering post-Transformers AI wave and learning from past episodes
1h 0m
Jul 1, 2023 · 2h 5m
Ronen Eldan and Yuanzhi Li of Microsoft Research discuss tiny model revolution, showing how small models can match larger ones through clever training
2h 5m
Jun 20, 2023 · 1h 12m
George Hotz discusses tinybox, a $15,000 'luxury AI computer' for local model training/inference with 738 FP16 TFLOPS and 144GB GPU RAM
1h 12m

Track New Episodes & Guest Appearances

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

Sign Up Free →