Play video
Low Level Technicals of LLMs: Daniel Han
AI Engineer session on Low Level Technicals of LLMs: Daniel Han. It adds practical context for how teams are building and operating AI systems in production.
Research archive, page 53
Browse entries 1249–1272 of 1531. Return to the first page to search and filter the complete collection.
Play video
Play video
Pydantic is STILL all you need: Jason Liu
AI Engineer session on Pydantic is STILL all you need: Jason Liu. It adds practical context for how teams are building and operating AI systems in production.
Play video
Building efficient hybrid context query for LLM grounding: Simrat Hanspal
AI Engineer session on Building efficient hybrid context query for LLM grounding: Simrat Hanspal. It adds practical context for how teams are building and operating AI systems in production.
Play video
Lessons From A Year Building With LLMs
AI Engineer session on Lessons From A Year Building With LLMs. It adds practical context for how teams are building and operating AI systems in production.
Play video
Insights on Building AI Teams — Heath Black, SignalFire
AI Engineer session on Insights on Building AI Teams, presented by Heath Black, SignalFire. It adds practical context for how teams are building and operating AI systems in production.
Play video
Keynote: The AI developer experience doesn't have to suck — why and how we built Modal
AI Engineer session on Keynote: The AI developer experience doesn't have to suck, presented by why and how we built Modal. It adds practical context for how teams are building and operating AI systems in production.
Play video
The Multimodal Future of Education: Stefania Druga
AI Engineer session on The Multimodal Future of Education: Stefania Druga. It adds practical context for how teams are building and operating AI systems in production.
Play video
The LLM Triangle: Engineering Principles for Robust AI Applications - Almog Baku:
AI Engineer session on The LLM Triangle: Engineering Principles for Robust AI Applications - Almog Baku:. It adds practical context for how teams are building and operating AI systems in production.
Play video
Accelerating Mixture of Experts Training With Rail Optimized InfiniBand Networking in Crusoe Cloud
AI Engineer session on Accelerating Mixture of Experts Training With Rail Optimized InfiniBand Networking in Crusoe Cloud. It adds practical context for how teams are building and operating AI systems in production.
Play video
Cohere for VPs of AI: Vivek Muppalla
AI Engineer session on Cohere for VPs of AI: Vivek Muppalla. It adds practical context for how teams are building and operating AI systems in production.
Play video
Everything you need to know about Fine-tuning and Merging LLMs: Maxime Labonne
AI Engineer session on Everything you need to know about Fine-tuning and Merging LLMs: Maxime Labonne. It adds practical context for how teams are building and operating AI systems in production.
Play video
The Rise of the AI Software Engineer: Jesse Han
AI Engineer session on The Rise of the AI Software Engineer: Jesse Han. It adds practical context for how teams are building and operating AI systems in production.
Play video
Substrate Launch: the API for modular AI
AI Engineer session on Substrate Launch: the API for modular AI. It adds practical context for how teams are building and operating AI systems in production.
Play video
AI Engineers: The Next Generation — Stefania Druga, Google Gemini
AI Engineer session on AI Engineers: The Next Generation, presented by Stefania Druga, Google Gemini. It adds practical context for how teams are building and operating AI systems in production.
Play video
Your LLM Ran Out of Knowledge — Now What?
AI Engineer session on Your LLM Ran Out of Knowledge, presented by Now What?. It adds practical context for how teams are building and operating AI systems in production.
![[Full Workshop] Llama 3 at 1,000 tok/s on the SambaNova AI Platform video thumbnail](https://i.ytimg.com/vi/z_Xh2MzqKDM/hqdefault.jpg)
Play video
[Full Workshop] Llama 3 at 1,000 tok/s on the SambaNova AI Platform
AI Engineer session on [Full Workshop] Llama 3 at 1,000 tok/s on the SambaNova AI Platform. It adds practical context for how teams are building and operating AI systems in production.
Play video
The Future of Knowledge Assistants: Jerry Liu
AI Engineer session on The Future of Knowledge Assistants: Jerry Liu. It adds practical context for how teams are building and operating AI systems in production.
Play video
10x Development: LLMs For the working Programmer - Manuel Odendahl
AI Engineer session on 10x Development: LLMs For the working Programmer - Manuel Odendahl. It adds practical context for how teams are building and operating AI systems in production.
Play video
New Claude Opus 4.8: 15 Things You May’ve Missed
The ‘best’ generally available AI model just dropped, but there is plenty I bet you missed about what it is, how it performs, and what the release tells us. 15 highlights from the 244 page system card, plus private testing, leader interview and more.
Play video
Your Agent Evolved. Your Evals Didn't. — Ameya Bhatawdekar, Braintrust
Teams built orchestration graphs because the models of 2024 could not be trusted to orchestrate, and then the models learned to orchestrate and the graphs became the thing holding them back.
Play video
Give the Agent a Budget, Not a Token — Sachin Malhotra, Anthropic
An agent tidying up after itself listed the workloads it no longer needed and deleted them.
Play video
How to build an AI-Native Health Company — Dan Feng, Maven Clinic
Implementation used to be the expensive step, so teams spent weeks settling requirements before anyone wrote code. Dan Feng's observation is that the cost moved. Building takes minutes now, and arguing is what is expensive. Planning at Maven Clinic changed to match.
Play video
Guardrails First: Engineering Member-Facing Health AI — Rashi Agrawal, Hinge Health
A healthy 60 year old man asked a popular AI assistant how to cut salt from his diet. It pointed him at sodium bromide. Three months later he arrived in an emergency room with paranoia and hallucinations, bromide at 200 times the safe level, and stayed three weeks.
Play video
Why Your Enterprise Tech Stack Isn’t Ready for AI Agents — Christopher Lovejoy & Saul Howard
The proof of concept works. It hits the accuracy targets, it is fast, it is cheap, and the room is happy. Then someone from compliance raises a hand and asks to see the audit trail, and the whole thing stops.