agentic AI
-
Artificial intelligence
OpenAI’s Atlas browser promises ultimate convenience. But the glossy marketing masks safety risks
If you want to try Atlas, the advice is straightforward: extreme caution.
-
Advances & challenges in foundation agents
Advances & challenges in foundation agents: Introduction to Part I – Core components of intelligent agents
At the heart of Liu and colleagues’ framework is a living loop.
-
Advances & challenges in foundation agents
Advances & challenges in foundation agents: Section 1.4 – Navigating this series
This series is structured to provide a comprehensive, modular, and interdisciplinary examination of intelligent agents.
-
Advances & challenges in foundation agents
Advances & challenges in foundation agents: Section 1.3.4 – Connections to existing theories
Liu and colleagues’ framework builds on and synthesizes several influential theories from AI, cognitive science, and neuroscience.
-
Advances & challenges in foundation agents
Advances & challenges in foundation agents: Section 1.3.3 – Biological inspirations
Liu and colleagues' agent framework, though fundamentally computational, finds its roots in biological systems.
-
Advances & challenges in foundation agents
Advances & challenges in foundation agents: Section 1.3.2 – Core concepts and notations in the agent loop
The agent framework architecture and a formal definition of foundation agents.
-
Advances & challenges in foundation agents
Advances & challenges in foundation agents: Section 1.3.1 – From language models to AI agents
To grant an LLM the street-smarts of an AI agent, we must graft on several faculties.
-
Advances & challenges in foundation agents
Advances & challenges in foundation agents: Section 1.3 – Foundation agents: a modular and brain-inspired AI agent framework
Principles that form the foundation of a proposed brain-inspired agent framework.
-
Advances & challenges in foundation agents
Advances & challenges in foundation agents: Section 1.2.1 – Brain functionalities and AI parallels
A biologically-grounded illustration and discussion highlighting which human cognitive functions are replicated in AI and which remain frontier challenges.
-
Advances & challenges in foundation agents
Advances & challenges in foundation agents: Section 1.2 – A parallel comparison between human brain and AI agents
LLM-powered agents differ significantly from human cognition across key dimensions.
