AI Engineer World's Fair 2024
Talks from AI Engineer World's Fair 2024, drafted from the AI Engineer channel's own playlists. Editorial metadata is best-effort parsed and under review.
Event 1
-
1 ↑4
Stop Making Models Bigger, Make Them Behave — Kobie Crawford, Snorkel
51.4K views 1.2K likes 70 comments
-
2 ↑9
How to Construct Domain Specific LLM Evaluation Systems: Hamel Husain and Emil Sedgh
21.6K views 591 likes 9 comments
-
3 ↑13
Lessons from the Trenches: Building LLM Evals That Work IRL: Aparna Dhinkaran
14.8K views 355 likes 9 comments
-
4 ↑17
Why Eval++ Is the Next Great Compute Primitive — Sunil Pai & Matt Carey, Cloudflare
9.5K views 183 likes 14 comments
-
5 ↑24
Self Driving Products: Product Signals to Pull Requests — Joshua Snyder, PostHog
7K views 158 likes 2 comments
-
6 ↑27
Evals Are Broken, Use Them Anyway — Ara Khan, Cline
5.3K views 98 likes 3 comments
-
7 ↑37
How Zapier Builds AI Products and Features with the Help of Braintrust: Ankur Goyal & Olmo Maldonado
3.6K views 62 likes 4 comments
-
8 ↑37
What It Actually Takes to Deploy GenAI Applications to Enterprises: Arjun Bansal and Trey Doig
3.6K views 53 likes 2 comments
-
9 ↑40
How agent o11y differs from traditional o11y — Phil Hetzel, Braintrust
3.1K views 46 likes 1 comments
-
10 ↑46
Judging LLMs: Alex Volkov
2.4K views 60 likes 4 comments
-
11 ↑52
The GenAI Maturity Curve or You Probably Don't Need Fine Tuning: Kyle Corbitt
1.7K views 37 likes 1 comments
