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
-
1 ↑3
[Full Workshop] Reinforcement Learning, Kernels, Reasoning, Quantization & Agents — Daniel Han
161.1K views 4.5K likes 142 comments
-
2 ↑12
How to Train Your Agent: Building Reliable Agents with RL — Kyle Corbitt, OpenPipe
66.1K views 1.6K likes 29 comments
-
3 ↑42
Training Agentic Reasoners — Will Brown, Prime Intellect
23.1K views 526 likes 20 comments
-
4 ↑47
AI Engineer World’s Fair 2025 - Reasoning + RL
19.2K views 204 likes 4 comments
-
5 ↑58
A Taxonomy for Next-gen Reasoning — Nathan Lambert, Allen Institute (AI2) & Interconnects.ai
16.2K views 288 likes 10 comments
-
6 ↑106
RL for Autonomous Coding — Aakanksha Chowdhery, Reflection.ai
7.8K views 154 likes 10 comments
-
7 ↑126
Road to 5 Million Tokens: Breaking Barriers in Long Context Training — Max Ryabinin, Together AI
6K views 122 likes 12 comments
-
8 ↑163
OpenThoughts: Data Recipes for Reasoning Models — Ryan Marten, Bespoke Labs
3.7K views 99 likes 1 comments
-
9 ↑280
Measuring AGI: Interactive Reasoning Benchmarks for ARC-AGI-3 — Greg Kamradt, ARC Prize Foundation
548 views 16 likes 0 comments
