Jacob Andreas
Artificial Intelligence
MIT researchers advance automated interpretability in AI models
As artificial intelligence models turn out to be increasingly prevalent and are...
Artificial Intelligence
Reasoning skills of enormous language models are sometimes overestimated
In relation to artificial intelligence, appearances will be deceiving. The mystery surrounding...
Artificial Intelligence
To construct a greater AI helper, start by modeling the irrational behavior of humans
To construct AI systems that may collaborate effectively with humans, it helps...
Artificial Intelligence
Natural language boosts LLM performance in coding, planning, and robotics
Large language models (LLMs) have gotten increasingly useful for programming and robotics...
Artificial Intelligence
Using ideas from game theory to enhance the reliability of language models
Imagine you and a friend are playing a game where your goal...
Artificial Intelligence
Large language models use a surprisingly easy mechanism to retrieve some stored knowledge
Large language models, resembling those who power popular artificial intelligence chatbots like...
Artificial Intelligence
Reasoning and reliability in AI
To ensure that natural language to be an efficient type of communication,...
Artificial Intelligence
AI agents help explain other AI systems
Explaining the behavior of trained neural networks stays a compelling puzzle, especially...
Recent posts
