AI Engineer World's Fair 2026
Talks from AI Engineer World's Fair 2026, drafted from the AI Engineer channel's own playlists. Editorial metadata is best-effort parsed and under review.
Event 1
-
301 —
Semantic Blindness: 500,000 Sensors Confused an LLM - Raahul Singh & Vanč Levstik, Phaidra
1.7K views 32 likes 4 comments
-
302 —
Your Fine-Tuned Model Is Tech Debt: A 50x ROI House of Cards — Dan Bjornn, Lease End
1.7K views 28 likes 2 comments
-
303 —
Your Agents Need a Save Button - Hamza Tahir, ZenML
1.6K views 35 likes 9 comments
-
304 —
Vending-Bench: Long-Horizon Agent Evals — Lukas Petersson, Andon Labs
1.6K views 27 likes 1 comments
-
305 —
The Next Medium: Why Real-Time Interactive Video Changes Everything — Ahmed Ahres, Reactor
1.6K views 26 likes 8 comments
-
306 —
Enterprise Agents Have a Structure Problem - Ishita Daga, Tesla
1.6K views 24 likes 3 comments
-
307 —
Let's integrate AI Agents in Event-Sourced Systems — Divakar Kumar, FlyersSoft
1.6K views 21 likes 4 comments
-
308 —
Bringing agents onto the world wide web — Paul Klein IV, Browserbase
1.5K views 28 likes 5 comments
-
309 —
Scaling to Long Horizons — Ross Taylor & Chengxi Taylor, General Reasoning
1.5K views 20 likes 1 comments
-
310 —
SWE-Marathon: Evaluating Coding Agents at Billion-Token Scale - Rishi Desai, Abundant AI
1.5K views 42 likes 3 comments
-
311 —
Training Krea 2: What matters in generative model training — Sangwu Lee, Krea.ai
1.5K views 23 likes 12 comments
-
312 —
Adaption Labs: Gradient-Free Continual Learning — Sara Hooker, Adaption
1.5K views 34 likes 1 comments
-
313 —
Your Agent Evolved. Your Evals Didn't. — Ameya Bhatawdekar, Braintrust
1.5K views 31 likes 1 comments
-
314 —
How Forward Deployed Engineering is done at Decagon — Sunny Rekhi
1.5K views 14 likes 1 comments
-
315 —
Serving 2 Million Models Without Melting: Scaling the Hugging Face Hub — Arek Borucki, Hugging Face
1.5K views 59 likes 6 comments
-
316 —
Trading Desks to Clinical Trials: Parallels in Applied Vertical AI — Ayush Bhardwaj, Allos AI
1.4K views 43 likes 4 comments
-
317 —
Agents Need Receipts, Not More Tool Calls - Armanas Povilionis, Alithea Bio
1.4K views 36 likes 6 comments
-
318 ↑1
Data and Environment Curation for Post-Training LLMs — Mahesh Sathiamoorthy, Bespoke Labs
1.4K views 28 likes 1 comments
-
319 ↓1
Voice In, Visuals Out: The Agony and the Ecstasy - Allen Pike, Forestwalk Labs
1.4K views 24 likes 6 comments
-
320 ↑1
Data Quality Is the Compute Multiplier — Ari Morcos, DatologyAI
1.4K views 39 likes 1 comments
-
321 ↓1
From Systems of Record to Systems of Context — Omri Bruchim & Tomer Ast, monday.com
1.4K views 25 likes 2 comments
-
322 —
Building an Agentic Video Editor for Mass Consumer — Ekaterina Deyneka, Reelful
1.4K views 27 likes 6 comments
-
323 —
Agents at Scale: Inside MiniMax's Model and the Infrastructure Behind It — Dan Fu and Olive Song
1.4K views 22 likes 2 comments
-
324 —
A Song of Types and Agents - Roberto Stagi, Ratel
1.4K views 26 likes 0 comments
-
325 —
The 100-Tool Agent Is a Trap - Sohail Shaikh & Ankush Rastogi, Prosodica
1.3K views 35 likes 1 comments
