2021 Air Street Capital The State of AI Report 2021 · page 51 of 188
The slide highlights the unreliability of human benchmarks in NLP, specifically referencing GPT-2 and GPT-3 evaluation.
Consulting deck · diagnosis · diagnose · dense density
Slide locked Sign in to view
Slide schematic 4/6
callout 0/1 image 1/1 list 1/1 metric 0/1 paragraph 1/1 title 1/1
2 without position callout 1 · metric 1
calloutmetric · primary
Components 6
callout infographic bullet primary paragraph headline
Tools 0
∅
No tools
No canon tool match is anchored to this slide.
Metrics 0
∅
No metrics
No metric insight is anchored to this slide.
Frameworks 0
∅
No frameworks
No framework match is anchored to this slide.