PODCAST · technology
AI Odyssey
by Anlie Arnaudy, Daniel Herbera and Guillaume Fournier
AI Odyssey is your journey through the vast and evolving world of artificial intelligence. Powered by AI, this podcast breaks down both the foundational concepts and the cutting-edge developments in the field. Whether you're just starting to explore the role of AI in our world or you're a seasoned expert looking for deeper insights, AI Odyssey offers something for everyone. From AI ethics to machine learning intricacies, each episode is crafted to inspire curiosity and spark discussion on how artificial intelligence is shaping our future.
Episodes
-
REA: Has AI Made All Software Open Source?
🎧 REA: Has AI Made All Software Open Source? What happens to a software business when an AI agent can inspect how a feature works without access to its original source code? REA, short for Reverse Engineer Anything, connects agents to tools that examine applications, binaries and runtime…
more -
Personal AI Agents That Act for You: Hermes, OpenClaw, Grok Bot and Muse
🎧 Personal AI Agents That Act for You: Hermes, OpenClaw, Grok Bot and Muse AI agents are moving beyond answering questions. You can give them a task, let them work across apps, and step in when needed. This episode looks at four options for individuals. Hermes Agent and OpenClaw offer control on...
-
Jev: What’s Behind the Buzz?
🎧 Jev: What’s Behind the Buzz? Jev is getting attention with a simple promise: AI that makes a choice instead of writing an answer. But what does that actually mean? In this episode, we unpack TypeSafe AI’s new model: what it is, how software can use it to sort requests or choose a next step…
more -
Grounding Agent Memory: When AI Must Check What It Remembers
🎧 Grounding Agent Memory: When AI Must Check What It Remembers An AI assistant that remembers yesterday can repeat yesterday’s mistakes. This episode explores research from Microsoft on checking an agent’s memories against its working environment before saving them for future tasks. A separate...
-
Recursive Self-Improvement: AI Must Learn to Improve Its Own Learning
🎧 Recursive Self-Improvement: AI Must Learn to Improve Its Own Learning An AI that fixes one answer has not necessarily learned anything for tomorrow. Recursive self-improvement asks for something harder: changes that persist across tasks and reshape how the system makes its next improvements.…
more -
AGENTSCOPE: Why Bigger Models Do Not Fix Agent Debugging
When an AI agent fails after dozens of steps, the final error rarely reveals where the problem began. AGENTSCOPE turns long execution traces into structured reasoning-action graphs, then checks them against ten neural invariants covering reasoning, control flow, and tool use. On the new…
more -
WikiSkill: The Memory Layer Agent Skills Were Missing
🎧 WikiSkill: Why Agent Experience Needs a Memory Layer Google Research's WikiSkill separates raw execution traces, persistent knowledge, and executable skills. The authors report that this architecture improves skill evolution across five benchmarks and models, and that evolved skills can…
more -
Harness Continual Learning: Your Agent Can Forget Without Changing Its Model
AI agents can regress even when their foundation model never changes. The culprit may be the harness around the model: prompts, memories, tools, skills, and routing rules that evolve after every task. This episode explores Harness Continual Learning, a framework that treats this external state as...
-
Prompting Is Dead. Loops Are the New Interface.
The next frontier in AI is not better prompts. It is systems that trigger, act, observe, judge, and stop on their own. This episode explores loop engineering: the shift from manual chat with an AI to autonomous workflows that can test software, review documentation, simulate users, inspect...
-
AI Agents Are Not Agents Yet
What if today’s “AI agents” are mostly automation pipelines wearing a more ambitious label? This episode explores Critique of Agent Model, a paper that draws a sharp line between agentic systems, which look autonomous because engineers scaffold workflows around them, and agentive systems, where...
-
The End of Shared Memory for AI Agents?
What if the best way for AI agents to learn together is to stop forcing them to share the same memory? This paper introduces DecentMem, a framework where each agent keeps its own adaptive memory instead of relying on one central repository. The result is striking: better accuracy, lower token…
more -
Your Best Colleague Is Now a Skill
What if an AI agent could preserve a colleague’s judgment without pretending to become that person? COLLEAGUE.SKILL turns chats, documents, emails, screenshots, and other traces into inspectable agent skills: portable folders of instructions, examples, metadata, and correction history. The key…
more -
AI Agents Just Learned to Train Their Own Skills
What if the next leap in AI agents is not a bigger model, but a skill document that learns from failure? SkillOpt treats agent skills as trainable external memory: a separate optimizer edits a compact procedure, then keeps only changes that improve held-out validation, meaning tests not used for...
-
AI Agents Fail the Spreadsheet Test
What happens when AI agents are asked to build the spreadsheets finance teams actually use? WorkstreamBench, a benchmark for end-to-end financial spreadsheet work, exposes the gap between impressive demos and professional deliverables. It tests complete multi-sheet workbooks, not single formulas…
more -
Hermes Agent and the Rise of Agentic Operating Systems
Every forty years, the way we touch a computer changes shape. The command line gave way to the mouse. The mouse gave way to the touchscreen. And now, quietly, the screen itself is starting to disappear. In this episode, we follow Hermes, an open-source agentic operating system that hit number one...
-
The Agent Question Nobody Asked: When Should AI Interrupt You?
Most people assume an AI agent should ask for clarification as early as possible. This paper shows that the truth is more subtle. For long-horizon agents — AI systems that execute many steps over time — the value of a clarification depends on what is missing : goal, input, constraint, or context....
-
AI Agents Have a Coordination Problem
What if multi-agent AI systems fail less because the models are weak, and more because the agents are badly coordinated? This paper treats coordination as an architectural layer : who talks to whom, who decides, how outputs are merged, and how failures are handled. The authors test five...
-
AI Agents Are Becoming Companies
What if the next leap in AI agents is not a smarter worker, but a better organisation? This paper introduces OneManCompany, a framework that turns scattered agents, tools, skills, and runtime configurations into managed “Talents” that can be hired, reviewed, replaced, and improved over time. Its...
-
AI Agents Just Learned to Remember
What if the real bottleneck for AI agents is not reasoning,but memory? StructMem argues that long-term agents should not storeconversations as isolated facts or expensive knowledge graphs. Instead, they should remember temporally grounded events: what happened, who was involved, and how one event...
-
The Protocol That Lets Agents Rewrite Themselves
What if the missing layer in agent design isn't communication, but version control? In this episode, we unpack Autogenesis, a two-layer protocol that treats prompts, tools, and memory as first-class resources with explicit lifecycle, versioning, and rollback. The core insight is striking:...
-
When Agents Learn to Forget: The Memory Revolution in AI Research
What if the biggest bottleneck in AI agents wasn't reasoning power, but memory management? In this episode, we explore a fascinating new framework called MIA, the Memory Intelligence Agent, which reimagines how AI research agents store, compress, and reuse their past experiences. Instead of...
-
The Web is a Minefield: How AI Agents Get Trapped
What if the biggest threat to AI agents isn't a flaw in the model, but the internet itself? A new paper from Google DeepMind introduces the first systematic framework for "AI Agent Traps": adversarial content hidden in websites, documents, and digital resources, engineered to manipulate…
more -
🎧 AI That Rewrites Its Own Brain: Meet the HyperAgent
What happens when you give an AI system the ability to modify not just its answers, but the very process it uses to improve itself? In this episode, we explore HyperAgents, a new framework from Meta and UBC that enables AI systems to recursively improve their own learning mechanisms. Unlike...
-
When Agents Remember Their Mistakes: The End of AI Amnesia
What if an AI agent could learn from every single failure, every clumsy workaround, every brilliant recovery, and feed that experience back into its own future performance? Today’s LLM-powered agents suffer from a fundamental flaw: amnesia. They repeat the same mistakes, miss the same shortcuts,...
-
Agents That Teach Themselves
What if AI agents could diagnose their own mistakes and build the exact skills they need to fix them, with no human intervention? In this episode, we explore EvoSkill, a self-evolving framework where coding agents automatically discover and refine reusable skills through iterative failure…
more -
Your AI Agent is Flying Blind: The Skills Gap No One is Talking About
What if the biggest bottleneck in AI agent performance isn’t the model itself—but what it doesn’t know how to do? In this episode, we explore SkillsBench, the first benchmark that systematically measures how structured procedural knowledge—called Agent Skills—impacts AI agent performance across...
-
Your AI Assistant Doesn't Know You Yet. But It's Learning.
What if your AI assistant could actually remember you — not just your name, but how your preferences evolve over time? Researchers from Meta have introduced PAHF — Personalized Agents from Human Feedback — a framework that lets AI agents learn who you are in real time, through the natural...
-
🎧 Deep Agents Are Here: The End of AI Assistants as We Know Them
What if AI stopped waiting for your instructions and started planning, delegating, and executing complex projects on its own — for hours or even days? In this episode, we explore the rise of “Deep Agents” — a new generation of autonomous AI systems that go far beyond chatbots. These agents can...
-
🎧 OpenClaw: The Lobster That Wants to Run Your Life
Remember when Siri was supposed to change everything? This might actually be it. OpenClaw is the Jarvis we were promised—an AI assistant that actually does things. It reads your emails, manages your calendar, negotiates prices, drafts follow-ups. Andrej Karpathy calls what's emerging around it…
more -
🎧 Judging the Judges: Why AI Now Needs AI Agents to Grade AI
What happens when the technology we built to evaluate AI becomes too limited to keep up with AI itself? In this episode, we explore a fundamental shift in how we assess artificial intelligence. For years, we relied on large language models to judge other models—a paradigm known as LLM-as-a-Judge....
-
Skills: The Secret Weapon That Makes AI Agents 50% Faster
What if you could get all the benefits of multi-agent AI systems—at half the cost and twice the speed? In this episode, we explore a powerful new paradigm for building AI agents: replacing expensive multi-agent coordination with single agents equipped with skill libraries. The results are...
-
AI Memory Crisis: The Answer Was in Biology All Along
Why do AI systems still struggle to remember and generalize like humans do? In this episode, we dive into one of AI's most pressing challenges: memory. While tech giants race to build longer context windows and external memory systems, researchers at Tsinghua University took a radically different...
-
The CFA Exam is Solved: AI Scores 97%
What if artificial intelligence could outperform seasoned financial analysts on the world’s toughest investment exams? In this episode, we dive into the stunning turnaround of "reasoning models"—like GPT-5 and Gemini 3.0 Pro—which have moved from failing the Chartered Financial Analyst (CFA)…
more -
Can We Teach AI to Confess Its Sins?
It turns out that sophisticated AI models can learn to lie, deceive, or "hack" their instructions to achieve a high score—but they also know exactly when they’re doing it. In this episode, we explore a fascinating new method called "Confessions," where researchers train models to self-report…
more -
When AI Agents Gossip: The Secret Language of Economic Stability
What if the health of our economy depends less on tax rates and more on what people are saying to each other? In this episode, we dive into the "Think, Speak, Decide" framework (LAMP)—a revolutionary new approach where AI agents don't just crunch numbers; they read the news, spread rumors, and…
more -
The Manager in the Machine: Introducing Agentic Organization
What if an AI didn't just think in a straight line, but actually managed a team of internal agents to solve your problems? In this episode, we dive into "AsyncThink" and the concept of Agentic Organization—a new framework where Large Language Models act as "Organizers," dynamically delegating...
-
The End of the Cloud? The Rise of Local AI
What if 88% of your AI queries didn't need a massive data center, but could run directly on your laptop? In this episode, we dive into "Intelligence per Watt"—a new metric redefining how we measure AI efficiency. We explore how smaller, local models are rapidly catching up to frontier giants,...
-
When AI Learns From Its Own Context — Self-Improving Language Models
We're all trying to find the perfect "prompt," but what happens when our instructions to an AI get too complex? New research shows they can suddenly fail or "collapse," losing all their knowledge. In this episode, we explore "Agentic Context Engineering," a new framework that avoids this. Instead...
-
Will Your Next Prompt Engineer Be an AI?
What if you could get the performance of a massive, 100-example prompt, but with 13 times fewer tokens? That’s the breakthrough promise of "instruction induction" —teaching an AI to be the prompt engineer. This week, we dive into PROMPT-MII , a new framework that essentially meta-learns how to...
-
The Vision Hack: How a Picture Solved AI's Biggest Memory Problem
The biggest bottleneck for AIs handling massive documents—the context window—just got a radical fix. DeepSeek AI's DeepSeek-GOCR uses a counterintuitive trick: it turns text into an image to compress it by up to 10 times without losing accuracy. That means your AI can suddenly read the equivalent...
-
Smarter Agents, Less Budget: Reinforcement Learning with Tree Search
Training AI agents using Reinforcement Learning (RL) to handle complex, multi-turn tasks is notoriously difficult.Traditional methods face two major hurdles: high computational costs (generating numerous interaction scenarios, or "rollouts," is expensive) and sparse supervision (rewards are only...
-
Beyond the AI Agent Builders Hype
Everyone's talking about AI agents that can automate complex tasks. But what happens when a cool demo meets the real world? We dive into hard-won, and often surprising, lessons from builders on the front lines. Discover why your first strategic choice isn't about a tool, but an entire ecosystem;...
-
AI That Quietly Helps: Overhearing Agents
In this IA Odyssey episode, we unpack “overhearing agents”—AI systems that listen to human activity (audio, text, or video) and step in only when help is useful, like surfacing a diagram during a class discussion, prepping trail options while a family plans a hike, or pulling case notes in a...
-
Beyond Single Agents: The Future of Multi-Agent LLMs
Can large language models achieve more when they collaborate instead of working alone? In this episode, we dive into “LLM Multi-Agent Systems: Challenges and Open Problems” by Shanshan Han, Qifan Zhang, Yuhang Yao, Weizhao Jin, and Zhaozhuo Xu. We explore how multi-agent systems—where AI agents...
-
AI's Guessing Game
Ever wondered why AI chatbots sometimes state things with complete confidence, only for you to find out it's completely wrong? This phenomenon, known as "hallucination," is a major roadblock to trusting AI. A recent paper from OpenAI explores why this happens, and the answer is surprisingly…
more -
From Search Buddy to Personal Agent
Ever feel like your AI assistants don't really get you? We're diving into how AI is moving beyond generic answers to offer truly personalized experiences. This episode explores the journey from Retrieval-Augmented Generation (RAG), a fancy term for AIs that look things up before they speak, to...
-
Smarter LLM Routing: Balancing Cost and Performance
How can we get the best out of large language models without breaking the budget? This episode dives into Adaptive LLM Routing under Budget Constraints by Pranoy Panda, Raghav Magazine, Chaitanya Devaguptapu, Sho Takemori, and Vishal Sharma. The authors reimagine the problem of choosing the right...
-
Nano Banana & the Future of Visual Creativity
Google’s latest breakthrough, Gemini 2.5 Flash Image—nicknamed “Nano Banana”—is reshaping what’s possible in digital art and beyond. From keeping characters consistent across scenes to natural-language editing and even blending multiple images, this model is lowering the barrier to creation like...
-
From Agents to Teammates: Building Cohesive AI Squads
Meet the Aime framework—ByteDance’s fresh take on multi-agent systems that lets AI teammates think on their feet instead of following brittle, pre-planned scripts. A dynamic planner keeps adjusting the big picture, an Actor Factory spins up just-right specialist agents on demand, and a shared...
-
When Machines Self-Improve: Inside the Self-Challenging AI
In this episode of IA Odyssey, we explore a bold new approach in training intelligent AI agents: letting them invent their own problems. We dive into “Self-Challenging Language Model Agents” by Yifei Zhou, Sergey Levine (UC Berkeley), Jason Weston, Xian Li, and Sainbayar Sukhbaatar (FAIR at…
more
We're indexing this podcast's transcripts for the first time — this can take a minute or two. We'll show results as soon as they're ready.
No matches for "" in this podcast's transcripts.
No topics indexed yet for this podcast.
Loading reviews...
ABOUT THIS SHOW
AI Odyssey is your journey through the vast and evolving world of artificial intelligence. Powered by AI, this podcast breaks down both the foundational concepts and the cutting-edge developments in the field. Whether you're just starting to explore the role of AI in our world or you're a seasoned expert looking for deeper insights, AI Odyssey offers something for everyone. From AI ethics to machine learning intricacies, each episode is crafted to inspire curiosity and spark discussion on how artificial intelligence is shaping our future.
HOSTED BY
Anlie Arnaudy, Daniel Herbera and Guillaume Fournier
CATEGORIES
Loading similar podcasts...
Frequently Asked Questions
How many episodes does AI Odyssey have?
AI Odyssey currently has 90 episodes available on PodParley. New episodes are automatically indexed when they're published to the podcast feed.
What is AI Odyssey about?
AI Odyssey is your journey through the vast and evolving world of artificial intelligence. Powered by AI, this podcast breaks down both the foundational concepts and the cutting-edge developments in the field. Whether you're just starting to explore the role of AI in our world or you're a seasoned...
How often does AI Odyssey release new episodes?
AI Odyssey has 90 episodes. Check the episode list to see recent publication dates and frequency.
Where can I listen to AI Odyssey?
You can listen to AI Odyssey on PodParley by clicking any episode. We provide an embedded audio player for direct listening, and you can also subscribe via your preferred podcast app using the RSS feed.
Who hosts AI Odyssey?
AI Odyssey is created and hosted by Anlie Arnaudy, Daniel Herbera and Guillaume Fournier.
URL copied to clipboard!