Episodes
-
Everything you need to run Mission Critical Inference (ft. DeepSeek v3 + SGLang)
DeepSeek V3 is a state-of-the-art model with 671 billion parameters, rated as the best open weights model as of January 2025.
-
[Ride Home] Simon Willison: Things we learned about LLMs in 2024
Not summarized yet
-
Beating Google at Search with Neural PageRank and $5M of H200s — with Will Bryk of Exa.ai
Not summarized yet
-
AI Engineering for Art — with comfyanonymous, of ComfyUI
Not summarized yet
-
Latent.Space 2024 Year in Review
Not summarized yet
-
2024 in Agents [LS Live! @ NeurIPS 2024]
Not summarized yet
-
2024 in Synthetic Data and Smol Models [LS Live @ NeurIPS]
Not summarized yet
-
2024 in Post-Transformers Architectures (State Space Models, RWKV) [LS Live @ NeurIPS]
Not summarized yet
-
2024 in Open Models [LS Live @ NeurIPS]
Not summarized yet
-
2024 in Vision [LS Live @ NeurIPS]
Not summarized yet
-
2024 in AI Startups [LS Live @ NeurIPS]
Not summarized yet
-
Windsurf: The Enterprise AI IDE - with Varun and Anshul of Codeium AI
Not summarized yet
-
Generative Video WorldSim, Diffusion, Vision, Reinforcement Learning and Robotics — ICML 2024 Part 1
Not summarized yet
-
Bolt.new, Flow Engineering for Code Agents, and >$8m ARR in 2 months as a Claude Wrapper
Not summarized yet
-
The new Claude 3.5 Sonnet, Computer Use, and Building SOTA Agents — with Erik Schluntz, Anthropic
Not summarized yet
-
Why Compound AI + Open Source will beat Closed AI
Fireworks AI focuses on building a compound AI ecosystem that combines multiple models to enhance AI capabilities across various modalities.
-
Agents @ Work: Lindy.ai
Not summarized yet
-
Agents @ Work: Dust.tt
Not summarized yet
-
In the Arena: How LMSys changed LLM Benchmarking Forever
Not summarized yet
-
How NotebookLM Was Made
Notebook LM emerged from Project Tailwind, focusing on generating audio content from various data sources.
Follow this show on AudioBrevity and new episodes get summarized for you. Create a free account