Über diesen Podcast
Agentic Horizons is an AI-hosted podcast exploring the cutting edge of artificial intelligence. Each episode dives into topics like generative AI, agentic systems, and prompt engineering, with content generated by AI agents based on research papers and articles from top AI experts. Whether you're an AI enthusiast, developer, or industry professional, this show offers fresh, AI-driven insights into the technologies shaping the future.
Folgen
Die neuesten 20 von 106 Folgen
- AI Storytelling with DOME · 15 Min. · Staffel 1 Folge 106In this episode, we explore DOME (Dynamic Hierarchical Outlining with Memory-Enhancement)—a groundbreaking AI method transforming long-form story generation. Learn how DOME…
- Intelligence Explosion Microeconomics · 18 Min. · Staffel 1 Folge 105This episode delves into intelligence explosion microeconomics, a framework for understanding the mechanisms driving AI progress, introduced by Eliezer Yudkowsky. It focuses on…
- Metacognitive Monitoring: A Human Ability Beyond AI · 7 Min. · Staffel 1 Folge 104The episode explores a study on the metacognitive abilities of Large Language Models (LLMs), focusing on ChatGPT's capacity to predict human memory performance. The study found…
- Building Living Software Systems with Generative & Agentic AI · 12 Min. · Staffel 1 Folge 103This episode explores how Generative and Agentic AI are transforming software development, leading to the rise of living software systems. It highlights the limitations of…
- Theory of Mind in LLMs · 14 Min. · Staffel 1 Folge 102This episode explores Theory of Mind (ToM) and its potential emergence in large language models (LLMs). ToM is the human ability to understand others' beliefs and intentions…
- Designing AI Personalities · 17 Min. · Staffel 1 Folge 101This episode explores the importance of AI personalities in human-computer interaction (HCI). As AI agents like Siri and ChatGPT become more integrated into daily life, their…
- FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning · 13 Min. · Staffel 1 Folge 100In this episode, we dive into FISHNET, an advanced multi-agent system transforming financial analysis. Unlike traditional approaches that fine-tune large language models, FISHNET…
- LLMs Know More Than They Show · 16 Min. · Staffel 1 Folge 99This episode discusses a research paper examining how Large Language Models (LLMs) internally encode truthfulness, particularly in relation to errors or "hallucinations." The…
- PDL: A Declarative Prompt Programming Language · 16 Min. · Staffel 1 Folge 98This episode covers PDL (Prompt Declaration Language), a new language designed for working with large language models (LLMs). Unlike complex prompting frameworks, PDL provides a…
- AI Self-Evolution Using Long Term Memory · 23 Min. · Staffel 1 Folge 97The episode examines Long-Term Memory (LTM) in AI self-evolution, where AI models continuously adapt and improve through memory. LTM enables AI to retain past interactions…
- Responsibility in a Multi-Value Strategic Setting · 16 Min. · Staffel 1 Folge 96This episode delves into “multi-value responsibility” in AI, exploring how agents are attributed responsibility for outcomes based on contributions to multiple, possibly…
- API-Based Web Agents · 15 Min. · Staffel 1 Folge 94This episode discusses the advantages of API-based agents over traditional web browsing agents for task automation. Traditional agents, which rely on simulated user actions…
- GUS-Net: Social Bias Classification with Generalizations, Unfairness, and Stereotypes · 10 Min. · Staffel 1 Folge 67This episode discusses GUS-Net, a novel approach for identifying social bias in text using multi-label token classification. Key points include: - Traditional bias detection…
- Google DeedMind's Talker-Reasoner Architecture · 10 Min. · Staffel 1 Folge 93This episode explores the Talker-Reasoner architecture, a dual-system agent framework inspired by the human cognitive model of "thinking fast and slow." The Talker, analogous to…
- A Framework for Representing Knowledge · 17 Min. · Staffel 1 Folge 92This episode explores Marvin Minsky's 1974 paper, "A Framework for Representing Knowledge," where he introduces frames as a method of organizing knowledge. Unlike isolated facts…
- RAG-ConfusionQA: A Benchmark for Evaluating LLMs on Confusing Questions · 10 Min. · Staffel 1 Folge 91This episode explores the challenges of handling confusing questions in Retrieval-Augmented Generation (RAG) systems, which use document databases to answer queries. It…
- Do LLMs Estimate Uncertainty Well? · 7 Min. · Staffel 1 Folge 90This episode explores the challenges of uncertainty estimation in large language models (LLMs) for instruction-following tasks. While LLMs show promise as personal AI agents…
- Stars, Stripes, and Silicon: Unravelling ChatGPT’s Bias · 9 Min. · Staffel 1 Folge 89This episode examines the societal harms of large language models (LLMs) like ChatGPT, focusing on biases resulting from uncurated training data. LLMs often amplify existing…
- Debug Smarter, Not Harder: AI Agents for Error Resolution in Computational Notebooks · 8 Min. · Staffel 1 Folge 88This episode explores the use of AI agents for resolving errors in computational notebooks, highlighting a novel approach where an AI agent interacts with the notebook…
- Interpretable End-to-end Neurosymbolic Reinforcement Learning Agents · 8 Min. · Staffel 1 Folge 101This episode delves into Neurosymbolic Reinforcement Learning and the SCoBots (Successive Concept Bottlenecks Agents) framework, designed to make AI agents more interpretable and…
