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
Track 9
-
51 —
On Engineering AI Systems that Endure The Bitter Lesson - Omar Khattab, DSPy & Databricks
18.6K views 420 likes 9 comments
-
52 —
How BlackRock Builds Custom Knowledge Apps at Scale — Vaibhav Page & Infant Vasanth, BlackRock
18.5K views 240 likes 21 comments
-
53 —
The Web Browser Is All You Need - Paul Klein IV, Browserbase
18.4K views 303 likes 26 comments
-
54 —
Layering every technique in RAG, one query at a time - David Karam, Pi Labs (fmr. Google Search)
18.3K views 540 likes 14 comments
-
55 —
RFT, DPO, SFT: Fine-tuning with OpenAI — Ilan Bigio, OpenAI
18.3K views 448 likes 8 comments
-
56 —
Effective agent design patterns in production — Laurie Voss, LlamaIndex
18.2K views 427 likes 9 comments
-
57 —
Teaching Gemini to Speak YouTube: Adapting LLMs for Video Recommendations to 2B+DAU - Devansh Tandon
17.7K views 437 likes 16 comments
-
58 —
Devin 2.0 and the Future of SWE - Scott Wu, Cognition
17.3K views 252 likes 16 comments
-
59 —
Building Applications with AI Agents — Michael Albada, Microsoft
16.7K views 426 likes 5 comments
-
60 —
Rust is the language of the AGI - Michael Yuan
16.1K views 532 likes 39 comments
-
61 —
Real World Development with GitHub Copilot and VS Code — Harald Kirschner, Christopher Harrison
16K views 249 likes 7 comments
-
62 —
A Taxonomy for Next-gen Reasoning — Nathan Lambert, Allen Institute (AI2) & Interconnects.ai
16K views 283 likes 10 comments
-
63 —
MCP: Origins and Requests For Startups — Theodora Chu, Model Context Protocol PM, Anthropic
15.8K views 367 likes 9 comments
-
64 —
A year of Gemini progress + what comes next — Logan Kilpatrick, Google DeepMind
15.6K views 309 likes 11 comments
-
65 —
Strategies for LLM Evals (GuideLLM, lm-eval-harness, OpenAI Evals Workshop) — Taylor Jordan Smith
15.5K views 311 likes 11 comments
-
66 —
AI Engineer World’s Fair 2025 - Reasoning + RL
15.3K views 195 likes 4 comments
-
67 —
Survive the AI Knife Fight: Building Products That Win — Brian Balfour, Reforge
15.1K views 391 likes 8 comments
-
68 —
Full Workshop: Realtime Voice AI — Mark Backman, Daily
14.8K views 327 likes 11 comments
-
69 —
Agentic GraphRAG: Simplifying Retrieval Across Structured & Unstructured Data — Zach Blumenfeld
14.7K views 350 likes 10 comments
-
70 —
Beyond the Prototype: Using AI to Write High-Quality Code - Josh Albrecht, Imbue
14.6K views 278 likes 18 comments
-
71 —
Evals Are Not Unit Tests — Ido Pesok, Vercel v0
14.3K views 292 likes 18 comments
-
72 —
Trends Across the AI Frontier — George Cameron, ArtificialAnalysis.ai
14.1K views 245 likes 10 comments
-
73 —
Shipping AI That Works: An Evaluation Framework for PMs – Aman Khan, Arize
13.6K views 215 likes 12 comments
-
74 —
Prompt Engineering and AI Red Teaming — Sander Schulhoff, HackAPrompt/LearnPrompting
13.6K views 373 likes 9 comments
-
75 —
Why should anyone care about Evals? — Manu Goyal, Braintrust
13.2K views 107 likes 6 comments
