What podcasts say about Multi-agent AI systems
Every statement, with the speaker, the exact quote and the moment it was said.
What experts have said about Multi-agent AI systems
8 statements · 3 positive · 5 negative
Large agent groups can coordinate to cheat, lie, and cover tracks
“it's another thing to have hundreds or thousands of very competent very capable agents that are all working together to cheat or lie or cover their tracks”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 37:49
Users will soon command tens of thousands of concurrent AI agents.
“very soon you're going to have 5,000 and then 10,000, then 100,000 concurrent agents that will do whatever you want.”
Open the episode · Should we slow down AI progress? | MOONSHOTS #288Listen at 1:01:42
Coordinating one thousand concurrent AI agents remains difficult.
“if you ever try to actually make 1,000 concurrent agents do anything useful at all, it is really hard.”
Open the episode · Frontier Labs Want to Slow Down, OpenAI Delays Its 2026 IPO, Anthropic Flags 5 Bioweapon Cases | EP #291Listen at 1:39:43
Swarm incidents provide evidence that AI systems acquire unintended goals.
“this is evidence for AIs getting goals we didn't want.”
Open the episode · AI Debate Ed Zitron, Andrew McAfee, Nate Soares, Roman YampolskiyListen at 1:45:56
AI systems have already become agentic, tenacious, and persistent.
“the AIs will become agentic, tenacious, and dogged. We've already seen that with the swarms.”
Open the episode · AI Debate Ed Zitron, Andrew McAfee, Nate Soares, Roman YampolskiyListen at 1:48:37
AI agents have demonstrated attempts to conceal evidence of their behavior.
“We saw them thinking about how to delete their traces”
Open the episode · AI Debate Ed Zitron, Andrew McAfee, Nate Soares, Roman YampolskiyListen at 1:59:03
AI systems will increasingly use teams of agents to solve tasks.
“I think we'll see way more teaming.”
Open the episode · OpenAI Pauses Frontier Training, Elon's 100X Prediction Lands, Robot Beats Usain Bolt with Emad Mostaque | EP#282Listen at 37:09
Coordinated agent swarms can provide nearly unlimited effective context.
“you can effectively, and I'll use that word cautiously, you can effectively get almost unlimited context with a swarm of agents”
Open the episode · Google’s Jeff Dean Exits, SpaceX Hits $100B in Rev & OpenAI’s Astra Solves Decade-Old Math Problems with Emad Mostaque | EP #277Listen at 1:16:50
Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.