Beyond LLMs - Agents, Emergent Abilities, Intermediate-Guided Reasoning, and BabyLM - Stanford CS25
Exploración de sistemas de IA autónomos, habilidades emergentes de LLMs, razonamiento guiado intermedio y modelos de lenguaje eficientes. Discusión sobre avances técnicos e implicaciones éticas en IA.
Building Embodied Autonomous Agents
Explore modular agents for visual navigation, 3D semantic mapping, and embodied instruction following. Learn about self-supervised learning, semantic search policies, and state-of-the-art performance in challenging environments.
Intelligence and Learning - Session 2
Live stream exploring evolving autonomous agents through a five-part coding challenge, combining genetic algorithms and steering behaviors. Practical application of concepts from "Intelligence and Learning" course.
How Vector Search with Qdrant Improves Workplace Efficiency
Discover how vector search technology and Qdrant power modern work environments, exploring implementation, scaling challenges, and practical applications in AI-driven business solutions.
Research and Innovation in AI-Driven Interactive Entertainment
Explore how AI revolutionizes gaming development through enhanced design processes, autonomous testing, and the emergence of intelligent virtual characters, while addressing ethical considerations and practical applications.
Graph-of-Thoughts: From Chain-of-Thoughts to Advanced AI Reasoning Algorithms
Explore the evolution of AI reasoning from Chain-of-Thoughts to Graph-of-Thoughts, discovering advanced algorithms that enhance autonomous agent capabilities and decision-making.
LLM-augmented Autonomous Agents - Achieving Goals with One Prompt Without LangChain
Discover how to orchestrate multiple AI agents using advanced prompt engineering, enabling complex task resolution through collaborative interactions and digital twin simulations - no LangChain required.
AFLOW: Automating Agentic Workflows for Large Language Models
Discover how AFLOW framework optimizes LLM workflows through automated code-based representations, specialized Monte Carlo Tree Search, and reusable operators to enhance AI performance while reducing computational costs.
Agent-based Mixture of Experts and LLM-augmented Autonomous Agents - A Tutorial on Dynamic Expert Generation
Discover how to create specialized AI expert agents through dynamic prompting, enabling tailored solutions for complex tasks from code generation to artistic design using LLM-augmented systems.
Testing and Development Tools for Autonomous AI Agents - Performance Analysis and Frameworks
Explore the latest developments in autonomous AI agents, testing frameworks, and RAG systems through Webarena, Microsoft's Geckopt, and Cohere's open-source toolkit.
AutoGPT and BabyAGI - Understanding Autonomous AI Agents for Large Language Models
Explore autonomous AI agents AutoGPT and BabyAGI, understanding their capabilities, risks, and integration with GPT-4 and LangChain for automated resource management and task execution.
Synthetic Reality: How Artificial Intelligence Will Shape the Metaverse and Everything
Explore AI's transformative role in shaping the Metaverse, from autonomous agents to synthetic avatars, and delve into its ethical implications, potential risks, and opportunities for innovation.
Computational Transcendence for Emergent Responsible Autonomy
Explore computational transcendence in autonomous systems, examining its impact on decision-making in supply chains and traffic management for enhanced efficiency and responsibility.
Learn AI Engineering: Building Autonomous Agent Systems with Llama 3 8B - Ollama
Explore autonomous agent creation using LLMs, focusing on Llama 3 8B and Claude 3 Haiku. Learn to build and expand a basic system with Python, incorporating functions and tools for task-solving.
Ethical Implications of In-Home Robots
Explore ethical challenges of in-home robots, including privacy, security, and social implications. Discusses robot personalities, authority, and potential misuse in various scenarios.
Agentic AI: Understanding Autonomous Agents in Business Process Automation
Explore the transformative potential of autonomous AI agents in business automation, from sales to cybersecurity, while understanding key challenges and implementation frameworks.
Building Reliable AI Agents - LLMs in Production Conference Part 2
Explore the fundamentals of building reliable AI agents, their business applications, and key challenges in agentic automation.
Transitioning from LLMs to Autonomous Agents in Programming and Software Engineering
Explore the evolution of LLMs into autonomous agents and their transformative impact on programming and software engineering practices, focusing on practical applications and future potential.
Agentic AI: Unlocking Emergent Behavior in LLMs for Adaptive Workflow Automation
Explore emergent AI capabilities and learn how agents combine LLMs with reasoning loops and tools to create adaptive, self-directing systems for advanced workflow automation.
From Rock-Paper-Scissors to BabyAGI - Harnessing LLMs with the Wolfram Language
Explore LLMs through rock-paper-scissors, then implement BabyAGI in Wolfram Language. Discover AI's decision-making and autonomous agent capabilities.
From RAG to Autonomous Apps with Weaviate and Gemini on Google Kubernetes Engine
Explore advanced RAG techniques using Weaviate and Gemini on GKE. Learn to deploy, ingest data, and enhance responses for building autonomous AI applications.