20:56
Stop Making Models Bigger, Make Them Behave — Kobie Crawdord, Snorkel
Kobie Crawford, developer advocate at Snorkel AI, presented research conducted in partnership with UC Berkeley's RLLM lab showing tha...
Sort by: Newest Items
There are 457 items in this page
34:00
Claude Fable 5 – Full 319 page Breakdown
AI Explained dedicates a full video to breaking down Anthropic's 319-page Claude Fable 5 system card — reading it cover to cover and...
11:13
RAG is dead, right?? — Kuba Rogut, Turbopuffer
Kuba Rogut, a deployed engineer at Turbopuffer, pushes back on the \"RAG is dead\" wave that swept AI social media in late 2025 and e...
15:50
Road to 5 Million Tokens: Breaking Barriers in Long Context Training — Max Ryabinin, Together AI
Max Ryabinin, VP of Research and Development at Together AI, presents the company's research project on extending transformer trainin...
24:51
Why Eval++ Is the Next Great Compute Primitive — Sunil Pai & Matt Carrie, Cloudflare
Cloudflare engineers Sunil Pai and Matt Carrie take the stage at the AI Engineer conference to explain how Cloudflare's Durable Objec...
26:27
Why More Context Makes Your Agent Dumber and What to Do About It — Nupur Sharma, Qodo
Nupur Sharma, an engineer at Qodo with a background in DevSecOps, presents hard-won lessons from deploying production agentic code re...
16:32
LLM Observability, Evaluation, Experimentation Platform — Dat Ngo, Arize
Dat Ngo, AI architect at Arize AI, presents a structured framework for making LLM systems observable, evaluable, and experimentally i...
19:04
Evals Are Broken, Use Them Anyway — Ara Khan, Cline
Ara Khan, an engineer on the Cline team, delivers a pointed critique of how the AI industry uses evaluation benchmarks — and why most...
06:49
Nanowhale-100m: Fascinating Implemention of DeepSeek-V4 Architecture
Fahd Mirza walks through Nanowhale-100M, a 110 million parameter language model built entirely from scratch—no borrowed weights—that...
25:20
Beyond Transcription: Building Voice AI That Understands Conversations — Hervé Bredin, pyannoteAI
Hervé Bredin, chief science officer and co-founder of pyannoteAI, presents a conference talk exploring what becomes possible when voi...
22:38
Building Agent Interfaces: Lessons from Chrome DevTools (MCP) for Agents — Michael Hablich, Google
Michael Hablich, Product Manager for Chrome DevTools at Google, shares four engineering lessons from building Chrome DevTools for Age...
44:53
It’s starting…
Matthew Berman breaks down Anthropic's newly published paper on recursive self-improvement, which traces the evolution of AI developm...
16:30
SWE-rebench: Lessons from Evaluating Coding Agents — Ibragim Badertdinov, Nebius
Ibragim Badertdinov, an AI researcher at Nebius with an unconventional background—a trained dentist turned NeurIPS and ICML author—pr...
23:25
The Art & Science of Benchmarking Agents — Vincent Chen, Snorkel AI
Vincent Chen, research fellow and co-founder at Snorkel AI, took the stage at AI Engineer to share meta-level lessons on what separat...
15:59
Nemotron 3 Ultra NVIDIA’s 550B Open Model
NVIDIA has released Nemotron 3 Ultra, a 550 billion parameter mixture-of-experts model built specifically for agentic workloads, and...
28:03
Text Diffusion — Brendon Dillon, Google DeepMind
Brendan Dillon, a research scientist at Google DeepMind, delivered a technically rigorous presentation at AI Engineer on text diffusi...