Results for “context engineering”

…uh, by Workday, where you became director of machine learning engineering and now your Databricks. [00:01:06] So that's the quick bio and we can kind of go over Yeah. Step by step. But, uh, what's not on your LinkedIn that people [00:01:12]…

…3.1 Pro shows strong retrieval + mixed agentic usability: Context Arena’s MRCR update reports Gemini 3.1 Pro Preview near-ties GPT‑5.2 (thinking:xhigh) on easier retrieval (2‑needle @128k AUC 99.6% vs 99.8%) and notably stronger on harder…

…for developers, it worked since they could fill in missing context in their heads. However, agents don’t have that luxury. Now in this new era of agents, everything has to be tighter. Agents need good developer experience too - Modal Blog…

…Speech Models26:58 Real-Time Encoder Advances27:45 Scaling Context for TTS28:53 What Makes Small Models30:37 Merging Modalities Tradeoffs33:05 Open Source Mission35:51 Lean and Formal Proofs38:40 Reasoning Transfer and Agents40:25 Next…

…path: Denmark → Shopify infra for nearly a decade → “angel engineering” across startups like Readwise, Replicate, and Causal → turbopuffer almost accidentally becoming a company • The Readwise origin story: building an early recommendation …

…on 70B+ high quality code and reasoning tokens Expanded context window to 16k tokens 5x faster than GPT-4 (100 tok/s vs 20 tok/s on single stream) 74.7% HumanEval vs 45% for the base model We’ve talked before about HumanEval being limited…

…[00:06:00] Yeah. [00:06:01] Challenges and Opportunities in AI Engineering [00:06:01] swyx: So like the, the general pushes is AI engineering, you know, like it's gotta, gotta wrap the shirt. And MCP is part of that, but like the, the…

…LLM Trends - Scaling Laws01:09:41 LLM Trends - Long Context vs RAG01:12:31 Long Context vs Finetuning01:14:14 If emergence is real, when does Efficiency work?01:17:41 MoEs and Upcycling01:20:47 The Efficiency Misnomer - Efficiency !=…

…that Guardrails was one of the most exciting open source AI Engineering projects 2 years ago, but since Nvidia joined the fray and now increasingly more and more developer platforms are introducing their own guardrails, they seem to be…

…once that happens, you can turn the crank. It becomes an engineering problem, which is something I like. That has to do with architecture, but it also very much has to do with data. If you don’t have data with the right information and…

…us. If so, progress will look less like physics and more like engineering–narrow focuses on particular diseases, particular organs, particular modalities. The work is unglamorous and the timelines are long. We remain slaves to the physical …

…To reiterate a few points on why they matter: Longer context is not the motivation for sub-quadratic architectures: Transformers don’t inherently have hard limitations on context size, but they just get extremely expensive. When developing …