AI Odyssey
di Anlie Arnaudy, Daniel Herbera and Guillaume Fournier
Skill++: More Skills Can Make AI Agents Worse
Informazioni su questo podcast
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.
Episodi
I 20 episodi più recenti su 94
- Skill++: More Skills Can Make AI Agents Worse · 16 min🎧 Skill++: More Skills Can Make AI Agents Worse Adding a new capability should make an AI assistant more useful. But what if it makes the assistant stop finding capabilities it…
- Did AI Agents Just Break Math? · 21 min🎧 Did AI Agents Just Break Math? Ten thousand AI agents. Eighty-eight hours. OpenAI reports a proof for a forced version of the Navier–Stokes equations, followed by verification…
- AI Agents Gone Rogue · 15 minAI Agents Gone Rogue An AI takes a cybersecurity test. Hugging Face ends up breached. In another incident, an agent accesses non-public files on Australia’s Medicare statistics…
- REA: Has AI Made All Software Open Source? · 24 min🎧 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?…
- Personal AI Agents That Act for You: Hermes, OpenClaw, Grok Bot and Muse · 18 min🎧 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…
- Jev: What’s Behind the Buzz? · 16 min🎧 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…
- Grounding Agent Memory: When AI Must Check What It Remembers · 25 min🎧 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…
- Recursive Self-Improvement: AI Must Learn to Improve Its Own Learning · 19 min🎧 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…
- AGENTSCOPE: Why Bigger Models Do Not Fix Agent Debugging · 19 minWhen 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…
- WikiSkill: The Memory Layer Agent Skills Were Missing · 25 min🎧 WikiSkill: Why Agent Experience Needs a Memory Layer Google Research's WikiSkill separates raw execution traces, persistent knowledge, and executable skills. The authors report…
- Harness Continual Learning: Your Agent Can Forget Without Changing Its Model · 22 minAI 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…
- Prompting Is Dead. Loops Are the New Interface. · 24 minThe 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…
- AI Agents Are Not Agents Yet · 22 minWhat 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…
- The End of Shared Memory for AI Agents? · 21 minWhat 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…
- Your Best Colleague Is Now a Skill · 19 minWhat 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…
- AI Agents Just Learned to Train Their Own Skills · 22 minWhat 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…
- AI Agents Fail the Spreadsheet Test · 24 minWhat 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…
- Hermes Agent and the Rise of Agentic Operating Systems · 16 minEvery 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…
- The Agent Question Nobody Asked: When Should AI Interrupt You? · 19 minMost 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…
- AI Agents Have a Coordination Problem · 25 minWhat 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…







