Stories by og_kalu

Using Transformers for Multi-Agent Reinforcement Learning

Multi-Agent Reinforcement Learning Is a Sequence Modeling Problem

Large Language Models Can Learn Rules

The Geometry of Truth: Emergent Linear Structure in How LLMs Represent Truth

Just Ask for Calibration: Eliciting Calibrated Confidence Scores from LLMs

Can LLMs provide useful feedback on research papers? A broad empirical analysis

Training language models with pause tokens

Boolformer: Symbolic Regression of Logic Functions with Transformers

The Dawn of Large Multimodal Models: Preliminary Explorations with GPT-4V(ision)

Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions

Large Language Models as Superpositions of Cultural Perspectives

DALL-E 3 will finish rolling out to all Bing Image users by 8PM PST today

Large Language Models Understand and Can Be Enhanced by Emotional Stimuli

The Internal State of a Large Language Model Knows When Its Lying

Dalle-3 Results and Requests

CodePlan: Repository-level Coding using LLMs and Planning

Optimal tic-tac-toe with GPT-4

Parallelizing non-linear sequential models over the sequence length

Dalle-3/GPT Screen Capture: Sky Dachshund [video]

GPT-3.5-turbo-instruct vs. Stockfish level 5

1
2
3
4
5
6
7
8
9