AI Safety Breakthrough
de AI SafeGuard
Dernier épisode
Navigating the New AI Security
Navigating the New AI Security
À propos de ce podcast
The future of AI is in our hands. Join AI SafeGuard on "AI Safety Breakthrough" as we explore the frontiers of AI safety research and discuss how we can ensure a future where AI remains beneficial for everyone. We delve into the latest breakthroughs, uncover potential risks, and empower listeners to become informed participants in the conversation about AI's role in society. Subscribe now and become part of the solution!
Intro about the author
J, graduated from Carnegie Mellon University, School of Computer Science, 10+ years in Cybersecurity, Cyber Threat Intelligence, Risk, Compliance, privacy and AI Safety.
Épisodes
- Navigating the New AI Security · 25 min · Saison 1 Épisode 10Welcome to Agentic AI Unlocked, your deep dive into the transformative world of Agentic AI—systems combining large language models with advanced reasoning and autonomous action…
- DeepSeek: A Disruptive Force in AI · 10 min · Saison 1 Épisode 9This episode explores DeepSeek, a Chinese AI startup challenging the AI landscape with its free alternative to ChatGPT. We'll examine DeepSeek's innovative architecture…
- VLSBench: A Visual Leakless Multimodal Safety Benchmark · 20 min · Saison 1 Épisode 8Are current AI safety benchmarks for multimodal models flawed? This podcast explores the groundbreaking research behind VLSBench, a new benchmark designed to address a critical…
- Adaptive Stress Testing for Language Model Toxicity · 15 min · Saison 1 Épisode 7This episode explores ASTPrompter, a novel approach to automated red-teaming for large language models (LLMs). Unlike traditional methods that focus on simply triggering toxic…
- Global Responsible AI Maturity: A Survey of 1000 Organizations · 19 min · Saison 1 Épisode 6This episode dives into the critical topic of Responsible AI (RAI), exploring how organizations worldwide are grappling with the ethical and practical challenges of AI adoption…
- Ivy-VL: A Lightweight Multimodal Model for Everyday Devices · 19 min · Saison 1 Épisode 5In this episode, we dive into Ivy-VL, a groundbreaking lightweight multimodal AI model released by AI Safeguard in collaboration with Carnegie Mellon University (CMU) and…
- Agent Bench: Evaluating LLMs as Agents · 13 min · Saison 1 Épisode 4Large Language Models (LLMs) are rapidly evolving, but how do we assess their ability to act as agents in complex, real-world scenarios? Join Jenny as we explore Agent Bench, a…
- Hacking AI for Good: Open AI’s Red Teaming Approach · 18 min · Saison 1 Épisode 3In this podcast, we delve into OpenAI's innovative approach to enhancing AI safety through red teaming—a structured process that uses both human expertise and automated systems…
- Surgical Precision: PKE’s Role in AI Safety · 14 min · Saison 1 Épisode 2Explore how Precision Knowledge Editing (PKE) refines AI for safety and ethical behavior in Surgical Precision: PKE’s Role in AI Safety. Join experts as we uncover the science…
