YoutuBlog
/
Channels
Podcasts
People
Topics
English
Recently updated channels
Pick one to see only that channel
Browse all channels →
20VC with Harry Stebbings
yesterday +188
JS
Jane Street
yesterday +119
AI Engineer
yesterday +1
硅谷101
2 days ago
MB
Matthew Berman
3 days ago +123
PragerU
3 days ago
Y Combinator
3 days ago
a16z
4 days ago +1
SemiAnalysis
4 days ago
GOTO Conferences
4 days ago
Results
1 articles
Sort
Newest
Newest
Oldest
Shortest first
Content type
Conference talks
Channel
AI Engineer
Topic
Benchmarks
10 slides
18:31
EN
AI Engineer
· Oct 25, 2026
Janie Gu and Suyeol Yun: Why Frontier Models Fail as Buy-Side Analysts
Janie Gu, Suyeol Yun · Google DeepMind
Janie Gu explains why benchmark scores can mislead, while Suyeol Yun presents MandateBench, which tests whether a model can turn a fund mandate into a defensible investment memo. The two talks show why real workflows, reproducible grading, and evidence-backed reasoning matter.
AI in finance
Benchmarks
Evals
+2