AI research

Researchers improve LLMs through ensemble of agents

Summary The performance of language models can be significantly improved by simply increasing the number of agents, according to a new paper. The Tencent research team’s paper, jokingly titled “More Agents Is All You Need,” examines the impact of adding more agents to a task. The title is an homage to the original Transformer paper, …

Researchers improve LLMs through ensemble of agents Read More »

Insights into the methods, datasets, and applications

Summary A new survey paper provides an in-depth look at the methods, datasets, and applications of how artificial intelligence could fundamentally change 3D development. 3D modeling has gained many new capabilities through the use of neural representations and generative AI models. A new survey paper provides a structured insight into the underlying methods, datasets, and …

Insights into the methods, datasets, and applications Read More »

DeepMind’s Self-Discover prompt technique encourages LLMs to think for themselves

Summary Researchers at Google DeepMind and the University of Southern California have unveiled Self-Discover, a framework that enables language models to find logical reasoning prompts for complex tasks on their own. Despite all the progress that has been made, logical reasoning is still the greatest challenge for large language models. To solve this problem, scientists …

DeepMind’s Self-Discover prompt technique encourages LLMs to think for themselves Read More »

AI agents could help better understand complex AI systems

Summary The Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT has developed a new way for LLMs to explain the behavior of other AI systems. The method is called Automated Interpretability Agents (AIAs), pre-trained language models that provide intuitive explanations for computations in trained networks. AIAs are designed to mimic the experimental process of …

AI agents could help better understand complex AI systems Read More »

Google DeepMind develops grandmaster-level chess AI with language model architecture

Summary Google DeepMind’s latest chess AI uses a language model architecture, plays at a high level, and shows that transformers can be more than just stochastic parrots. Researchers at Google DeepMind have developed an AI model that plays chess at a grandmaster level without relying on the complex search algorithms or heuristics that have characterized …

Google DeepMind develops grandmaster-level chess AI with language model architecture Read More »

Can GPT-4 plan your next vacation? TravelPlanner benchmark reveals the harsh truth

Summary The TravelPlanner benchmark is designed to test whether a language model can plan a trip. In the first tests, all models fail – including GPT-4. Researchers from Fudan University, Ohio State University, Pennsylvania State University, and Meta AI have developed a new benchmark that tests the ability of AI-driven language agents to create complex …

Can GPT-4 plan your next vacation? TravelPlanner benchmark reveals the harsh truth Read More »

Apple releases a capable open-source model for image editing with text

Summary AI image creation has made great strides recently, but image processing has lagged behind. Until now, that is, because Apple is demonstrating a method that understands and executes complex text instructions for image editing. Working with researchers at the University of California, Apple has developed a new open-source AI model that can edit images …

Apple releases a capable open-source model for image editing with text Read More »

How GPT-4 can learn to make decisions in dynamic scenarios

Summary Researchers at East China Normal University and Microsoft Research Asia have been studying how large language models such as GPT-4 perform in dynamic, interactive scenarios. The team wanted to find out how well language models could make choices in rapidly changing contexts that reflect the ever-changing strategies of the business and financial world, where …

How GPT-4 can learn to make decisions in dynamic scenarios Read More »

Can you catch ’em all? Meet PokéLLMon, the AI agent taking on human Pokémon players

Summary PokéLLMon is a language model-based AI agent that can beat humans at Pokémon. PokéLLMon uses large language models, wiki entries, and a form of reinforcement learning to create an AI agent that is comparable to human players. The Georgia Institute of Technology team sees the project as a test bed for developing agents that …

Can you catch ’em all? Meet PokéLLMon, the AI agent taking on human Pokémon players Read More »

AI agents can increase military escalation and nuclear risks, study says

Summary Governments are testing the use of AI to help make military and diplomatic decisions. A new study finds that this comes with a risk of escalation. In the Georgia Institute of Technology and Stanford University study, a team of researchers examined how autonomous AI agents, particularly advanced generative AI models such as GPT-4, can …

AI agents can increase military escalation and nuclear risks, study says Read More »

Scroll to Top