AI Safety Breakthrough
AI SafeGuard
0
AI Safety Breakthrough, hosted by AI SafeGuard, explores the latest developments in AI safety research. Each episode examines potential risks and breakthroughs, aiming to keep AI beneficial for society. The show empowers listeners to become informed participants in conversations about AI's role. The host brings expertise from Carnegie Mellon and years in cybersecurity and AI safety.
Episodes
-
Navigating the New AI Security 13.08.2025 25mWelcome 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. These intelligent agents promise to disrupt industries, yet introduce a fundamentally new threat surface. Risks like memory poisoning, tool misuse, prompt injection, and insider threats highlight the urgent need for robust security and real-time governance.The OWASP GenAI Security Project aims to provide actionable insights into these challenges, helping organizations responsibly develop, deploy, and govern agentic AI.... -
DeepSeek: A Disruptive Force in AI 03.02.2025 10mThis episode explores DeepSeek, a Chinese AI startup challenging the AI landscape with its free alternative to ChatGPT. We'll examine DeepSeek's innovative architecture, including Mixture-of-Experts (MoE) and Multi-head Latent Attention (MLA), which optimize efficiency. The discussion will highlight DeepSeek's use of reinforcement learning (RL) and its impact on reasoning capabilities, as well as how its open-source approach is democratizing AI access and innovation.We will also discuss ethical concerns, the competitive advantages and disadvantages of US-based models, and how DeepSeek is impac... -
VLSBench: A Visual Leakless Multimodal Safety Benchmark 26.01.2025 19mAre current AI safety benchmarks for multimodal models flawed? This podcast explores the groundbreaking research behind VLSBench, a new benchmark designed to address a critical flaw in existing safety evaluations: visual safety information leakage (VSIL)We delve into how sensitive information in images is often unintentionally revealed in the accompanying text prompts, allowing models to identify unsafe content based on text alone, without truly understanding the visual risks This "leakage" leads to a false sense of security and a bias towards simple textual alignment methods.Tune in to unders... -
Adaptive Stress Testing for Language Model Toxicity 20.01.2025 14mThis episode explores ASTPrompter, a novel approach to automated red-teaming for large language models (LLMs). Unlike traditional methods that focus on simply triggering toxic outputs, ASTPrompter is designed to discover likely toxic prompts – those that could naturally emerge during regular language model use. The approach uses Adaptive Stress Testing (AST), a technique that identifies likely failure points, and reinforcement learning to train an "adversary" model. This adversary generates prompts that aim to elicit toxic responses from a "defender" model, but importantly, these prompts have... -
Global Responsible AI Maturity: A Survey of 1000 Organizations 16.01.2025 18mThis 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. We'll be drawing insights from a comprehensive survey of 1000 organizations across 20 industries and 19 geographical regions -
Ivy-VL: A Lightweight Multimodal Model for Everyday Devices 09.12.2024 18mIn 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 Stanford University. With only 3 billion parameters, Ivy-VL processes both image and text inputs to generate text outputs, offering an optimal balance of performance, speed, and efficiency. Its compact design supports deployment on edge devices like AI glasses and smartphones, making advanced AI accessible on everyday hardware.Join us as we explore Ivy-VL's development, real-world applications, and how this collaborative effo... -
Agent Bench: Evaluating LLMs as Agents 27.11.2024 13mLarge 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 new benchmark designed to evaluate LLMs in diverse environments, from operating systems to digital card games. We'll delve into the key findings, including the strengths and weaknesses of different LLMs and the challenges of developing truly intelligent agents. -
Hacking AI for Good: Open AI’s Red Teaming Approach 24.11.2024 17mIn 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 to identify potential risks in AI models. We explore how OpenAI collaborates with external experts to test frontier models and employs automated methods to scale the discovery of model vulnerabilities. Join Jenny as we discuss the value of red teaming in developing safer, more reliable AI systems. -
Surgical Precision: PKE’s Role in AI Safety 24.11.2024 13mExplore 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, challenges, and breakthroughs shaping trustworthy AI. Perfect for tech enthusiasts and professionals alike, this podcast reveals how PKE ensures AI serves humanity responsibly.
Popular in
The podcast also appears in the podcast charts of these countries.