AI Engineer World's Fair 2025
Talks from AI Engineer World's Fair 2025, drafted from the AI Engineer channel's own playlists. Editorial metadata is best-effort parsed and under review.
Event 1
-
151 —
Building Agents (the hard parts!) - Rita Kozlov, Cloudflare Watched
4.9K views 89 likes 1 comments
-
152 —
New York Times' Connections: A Case Study on NLP in Word Games — Shafik Quoraishee, NYT Games Watched
4.9K views 111 likes 3 comments
-
153 —
Veo 3 for Developers — Paige Bailey, Google DeepMind Watched
4.9K views 98 likes 4 comments
-
154 —
AI Engineering with the Google Gemini 2.5 Model Family - Philipp Schmid, Google DeepMind Watched
4.9K views 102 likes 4 comments
-
155 —
GPU-less, Trust-less, Limit-less: Reimagining the Confidential AI Cloud - Mike Bursell Watched
4.8K views 670 likes 12 comments
-
156 —
The Unofficial Guide to Apple’s Private Cloud Compute - Jmo, CONFSEC Watched
4.7K views 79 likes 5 comments
-
157 —
Form factors for your new AI coworkers — Craig Wattrus, Flatfile Watched
4.6K views 75 likes 4 comments
-
158 ↑1
Why you should care about AI interpretability - Mark Bissell, Goodfire AI Watched
4.6K views 149 likes 4 comments
-
159 ↓1
Are MCPs Overhyped? A Rant about MCPs — Henry Mao, Smithery Watched
4.6K views 78 likes 11 comments
-
160 —
Knowledge Graphs in Litigation Agents — Tom Smoker, WhyHow Watched
4.4K views 125 likes 3 comments
-
161 —
Excalidraw: AI and Human Whiteboarding Partnership - Christopher Chedeau Watched
4.4K views 91 likes 4 comments
-
162 —
From Mixture of Experts to Mixture of Agents with Super Fast Inference - Daniel Kim & Daria Soboleva Watched
4.3K views 84 likes 6 comments
-
163 —
Full Spec MCP: Hidden Capabilities of the MCP spec — Harald Kirschner, Microsoft/VSCode Watched
4.3K views 62 likes 11 comments
-
164 —
Scaling AI Agents Without Breaking Reliability — Preeti Somal, Temporal Watched
4.2K views 83 likes 6 comments
-
165 —
Fuzzing in the GenAI Era — Leonard Tang, Haize Labs Watched
4.1K views 74 likes 10 comments
-
166 —
GraphRAG methods to create optimized LLM context windows for Retrieval — Jonathan Larson, Microsoft Watched
4.1K views 114 likes 3 comments
-
167 —
Text-to-Speech Data Preparation and Fine-tuning Workshop - Ronan McGovern Watched
4.1K views 117 likes 2 comments
-
168 —
Production software keeps breaking and it will only get worse — Anish Agarwal, Traversal.ai Watched
4K views 85 likes 5 comments
-
169 —
The Demo I Wish I'd Had: OpenAI's Agents SDK... serverless! - Brook Riggio Watched
4K views 97 likes 15 comments
-
170 —
Why We Don’t Need More Data Centers - Dr. Jasper Zhang, Hyperbolic Watched
4K views 69 likes 7 comments
-
171 —
Events are the Wrong Abstraction for Your AI Agents - Mason Egger, Temporal.io Watched
4K views 115 likes 8 comments
-
172 —
Why ChatGPT Keeps Interrupting You — Dr. Tom Shapland, LiveKit Watched
4K views 105 likes 13 comments
-
173 —
Turning Fails into Features: Zapier’s Hard-Won Eval Lessons — Rafal Willinski, Vitor Balocco, Zapier Watched
3.9K views 77 likes 7 comments
-
174 —
Good design hasn’t changed with AI — John Pham, SF Compute Watched
3.9K views 122 likes 5 comments
-
175 —
How to build world-class AI products — Sarah Sachs (AI lead @ Notion) & Carlos Esteban (Braintrust) Watched
3.8K views 60 likes 4 comments
Every video on this page is marked watched.