| The First Mechanistic Interpretability Frontier Lab — Myra Deng & Mark Bissell of Goodfire AI …Myra + Mark’s path: Palantir (health systems, forward-deployed engineering) → Goodfire early team; Two Sigma → Head of Product, translating frontier interpretability research into a platform and real-world deployments What… Podcast · Latent.Space · 2026-02-06 | Podcast | Latent.Space | 2026-02-06 |
| From RLHF to RLHB: The Case for Learning from Human Behavior - with Jeffrey Wang and Joe Reeve of Amplitude …in a foreign country. Most prompt engineers and prompt engineering tooling also tend to focus on pre-production prototyping, but could also benefit from A/B testing their prompts in the real world. In short, AI may need Analytics more than … Podcast · Latent.Space, Jeffrey Wang, Joe Reeve · 2023-06-08 | Podcast | Latent.Space, Jeffrey Wang, Joe Reeve | 2023-06-08 |
| Latent.Space 2024 Year in Review …to the 100th Episode!00:19 Reflecting on the Journey00:47 AI Engineering: The Rise and Impact03:15 Latent Space Live and AI Conferences09:44 The Competitive AI Landscape21:45 Synthetic Data and Future Trends35:53 Creative Writing with… Podcast · Latent.Space · 2024-12-31 | Podcast | Latent.Space | 2024-12-31 |
| [State of RL/Reasoning] IMO/IOI Gold, OpenAI o3/GPT-5, and Cursor Composer — Ashvin Nair, Cursor …co-design that keeps engineers in the loop instead of context-switching into ADHD hell, and his bet that the next paradigm shift is continual learning with infinite memory—where models experience something once (a bug, a mistake, a user… Podcast · Latent.Space · 2025-12-30 | Podcast | Latent.Space | 2025-12-30 |
| [State of Code Evals] After SWE-bench, Code Clash & SOTA Coding Benchmarks recap — John Yang …helping humans understand their own codebases, and automatic context engineering for LLMs (research sub-agents) The vision: CodeClash as a testbed for human-AI collaboration—vary the setup (solo agent, multi-agent, human+agent), freeze… Podcast · Latent.Space · 2025-12-31 | Podcast | Latent.Space | 2025-12-31 |
| The Creators of Model Context Protocol …bat. What is MCP? Justin/David [00:00:43]: Yeah, sure. So Model Context Protocol, or MCP for short, is basically something we've designed to help AI applications extend themselves or integrate with an ecosystem of plugins, basically. The… Podcast · Latent.Space · 2025-04-03 | Podcast | Latent.Space | 2025-04-03 |
| Agents @ Work: Lindy.ai …these examples for future tasks and injecting them into the context window. So that's the kind of capability that makes a huge difference for users. That's the bottleneck today. It's really like good old engineering and product work. Swyx… Podcast · Latent.Space · 2024-11-15 | Podcast | Latent.Space | 2024-11-15 |
| ICLR 2024 — Best Papers & Talks (Benchmarks, Reasoning & Agents) — ft. Graham Neubig, Aman Sanger, Moritz Hardt) …Safe AGI03:36:56 A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis03:48:43 MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework04:00:51 Bonus: Notable Related Papers on LLM Capabilities… Podcast · Latent.Space · 2024-06-10 | Podcast | Latent.Space | 2024-06-10 |
| Windsurf: The Enterprise AI IDE - with Varun and Anshul of Codeium AI …one particular piece of information out of all this potential context. That's not really what actually is necessary for doing software engineering because code is a super distributed knowledge store. You actually want to pull in snippets… Podcast · Varun Mohan, Latent.Space, Anshul Ramachandran · 2024-12-13 | Podcast | Varun Mohan, Latent.Space, Anshul Ramachandran | 2024-12-13 |
| How to train a Million Context LLM — with Mark Huang of Gradient.ai …AI engineers. Exactly a year ago, we declared the Beginning of Context=Infinity when Mosaic made their breakthrough training an 84k token context MPT-7B. MPT-7B and The Beginning of Context=Infinity — with Jonathan Frankle and Abhinav… Podcast · Latent.Space · 2024-05-30 | Podcast | Latent.Space | 2024-05-30 |
| Why the Frontier Ecosystem must be Open — Matei Zaharia and Reynold Xin, Databricks …data corruption,” why HTAP has been the holy grail of database engineering, and why Databricks thinks LTAP gets most of the benefits by unifying the storage layer instead of collapsing every query engine. We also cover Databricks’… Podcast · Latent.Space · 2026-06-24 | Podcast | Latent.Space | 2026-06-24 |
| Building Snipd: The AI Podcast App for Learning …actually part of the prompt. Um, so this is all prompt engine. Engineering, um, uh, you should be able to click on it. Yeah, I clicked on it. Um, this is all prompt engineering with how to provide the, the context, you know, we, because we … Podcast · Latent.Space · 2025-03-14 | Podcast | Latent.Space | 2025-03-14 |