2024 Air Street Capital The State of AI Report 2024

Slide locked Sign in to view

Slide schematic 6/6

list 4/4 table 1/1 title 1/1

Components 6

bullet bullet bullet bullet data headline

Tools 2

Action Titles slide · 88%

Title 'LLMs still struggle with planning and simulation tasks'

Table data slide · 70%

Table 2: Average accuracy per game of GPT-4 predicting the whole state transitions (F) as well as action-driven transitions (Fact) and environment-driven transitions (Fenv).

Metrics 0

∅

No metrics

No metric insight is anchored to this slide.

Frameworks 0

∅

No frameworks

No framework match is anchored to this slide.

Find anything

Includes a data table comparing LLM, Human, and No-rule performance across different game types and transition metrics.