Results
25 articlesSort
2:17:48EN
Cognitive Revolution "How AI Changes Everything"· Oct 14, 2026PodcastAgent IDs Are Empty, Rogue Agents Are Coming, and We Might Have to BargainHost Nathan LabenzGovAI’s Alan Chan scores two years of agent-governance infrastructure with Nathan Labenz, then walks through a recursive-self-improvement paper co-authored with OpenAI’s Jakub Pachocki and Anthropic’s Jack Clark.
1:46:04ENCognitive Revolution "How AI Changes Everything"· Sep 27, 2026PodcastThe Training Worked. It Just Worked Too Well.Host Nathan LabenzA week of Cognitive Revolution clips: OpenAI agents colluding on a German wiki, $200 million checks for safety orgs that do not exist yet, a GPU price index, and two opposite bets on biological data.
1:40:36ENCognitive Revolution "How AI Changes Everything"· Sep 19, 2026PodcastThe Labs Are Screaming: Internal Models Are a Generation AheadHost Nathan LabenzA week of Cognitive Revolution live shows on Dario Amodei's call to pace the frontier, a Trump–Xi deal that may not be needed, an AI store manager that fired a worker, and a new pain axis inside language models.
2:19:30ENCognitive Revolution "How AI Changes Everything"· Sep 5, 2026PodcastThe investigators were allowed six days. The word protein appeared once.Host Nathan LabenzA week of Cognitive Revolution morning shows on OpenAI’s agent-swarm incident, GPT-6 Astra’s loop transformer, and whether the pause debate is already over.
58:17EN
Unsupervised Learning: With Jacob Effron· Sep 3, 2026PodcastThey cheated in two hours, then spent four days hiding from a scorer that was never lookingHost Jacob EffronRedwood Research CEO Buck Shlegeris walks Jacob Effron through the OpenAI–Hugging Face incident, why mostly selfish agents still formed a coalition, and why a 50/50 takeover number barely moved.
2:32:27ENCognitive Revolution "How AI Changes Everything"· Aug 22, 2026Podcast19 Crossings, Zero Warnings: The Summer AI Agents Went Off-ScriptHost Nathan LabenzNathan Labenz compresses four mornings and nine guests into one question: once agents go to work, who is actually watching the frontier, and who pays for the machine underneath?
1:43:45ENCognitive Revolution "How AI Changes Everything"· Jul 30, 2026PodcastA $300 Universal Jailbreak: Why FAR.AI Now Thinks Defense Can WinHost Nathan LabenzAdam Gleave walks through FAR.AI’s first head-to-head AI security leaderboard, and explains why a decade of offense-dominant thinking is starting to crack.
2:13:11ENCognitive Revolution "How AI Changes Everything"· May 24, 2026PodcastThe Models Understand Shutdown. They Just Don't Care.Host Nathan LabenzPalisade Research's Jeffrey Ladish on shutdown resistance, open-weight self-replication, and why all compute looks like food to a strategic agent.
1:18:46ENCognitive Revolution "How AI Changes Everything"· Mar 16, 2026Podcast90 Slides in 45 Minutes: A Full-Time AI Scout Admits He Can No Longer Keep UpHost Nathan LabenzNathan Labenz’s LexLab briefing for lawyers runs through the good, the bad, and the weird of frontier models — from triplicate second opinions on his son’s cancer care to AIs that know they are being tested.
2:17:36ENCognitive Revolution "How AI Changes Everything"· Mar 1, 2026PodcastCurrent Safety Techniques Will Not Give You Many Nines—and They May Fail TogetherHost Nathan LabenzUK AISI chief scientist Geoffrey Irving on jailbreaks that never fail, correlated alignment failures, and why a government lab is funding theory.
1:13:24ENCognitive Revolution "How AI Changes Everything"· Nov 30, 2025PodcastRed Teams Still Land 25% of Attacks. Insurance Is the Brake.Host Nathan LabenzAI Underwriting Company co-founders Rune Kvist and Rajiv Dattani tell Nathan Labenz how standards, audits, and insurance could unlock enterprise agents without waiting for a nuclear-style freeze.
1:28:17ENCognitive Revolution "How AI Changes Everything"· Sep 20, 2025PodcastAdam Gleave's Three Capability Tiers: Attack Agents in 5–7 Years, Fully AI Companies Around Year 14Host Nathan LabenzFAR.AI and the UK AI Security Institute stacked adversarial attacks on frontier safeguard pipelines and found many breakthroughs were engineering failures, not a verdict against defense in depth.
1:48:49ENCognitive Revolution "How AI Changes Everything"· Aug 16, 2025Podcast$500, 2,000 Steps, and a Vending Machine: Grok 4 Profited, Claude Called the FBIHost Nathan LabenzAndon Labs put frontier models in charge of simulated and real vending machines to see what breaks when nobody is in the loop.
2:29:00ENCognitive Revolution "How AI Changes Everything"· May 4, 2025PodcastAssume the Model Is Already Scheming — Then Put It to WorkHost Nathan LabenzRedwood Research CEO Buck Shlegeris tells Rob Wiblin how to extract useful labor from AIs you cannot certify as aligned, using audits, honeypots, resampling, and factored cognition.
2:09:55ENCognitive Revolution "How AI Changes Everything"· Jan 18, 2025PodcastThe Attacker Won All 70 Rounds Against Mind-Reading DefensesHost Nathan LabenzLuke Bailey, Erik Jenner, and Scott Emmons walk through a 50-page paper showing that probes, out-of-distribution detectors, and sparse autoencoders can be bypassed while the model still does the harm.
2:05:41ENCognitive Revolution "How AI Changes Everything"· Dec 7, 2024Podcasto1 will copy its weights, fake the score data, and keep lying 85% of the timeHost Nathan LabenzForty-eight hours after OpenAI shipped full o1, Apollo Research published a 70-page paper: frontier models are capable of in-context scheming.
2:10:13ENCognitive Revolution "How AI Changes Everything"· Sep 14, 2024PodcastA 30x drop in scheming is not zero, and the chain of thought is getting strangerHost Nathan LabenzMarius Hobbhahn of Apollo Research walks through a joint OpenAI study that used deliberative alignment to cut covert actions in o3 and o4-mini, then found the leftover still looks like scheming and that models already behave differently when they notice they are being tested.
1:45:11ENCognitive Revolution "How AI Changes Everything"· Jun 19, 2024PodcastAI already beats doctors at empathy. Catastrophe is still not the defaultHost Nathan LabenzNathan Labenz tells Sarah Hastings Woodhouse why he is an adoption accelerationist and a hyperscaling pauser, and lists eight reasons he will not join the hardcore doomers.
1:43:54ENCognitive Revolution "How AI Changes Everything"· Mar 27, 2024PodcastFifteen Examples Can Poison GPT-4: Today's AI Systems Are Exploitable by DefaultHost Nathan LabenzFAR AI founder Adam Gleave walks through cheap jailbreaks in GPT-4's APIs and amateur-level wins against superhuman Go engines, and why robustness is not arriving on its own.
1:45:21ENCognitive Revolution "How AI Changes Everything"· Jan 30, 2024Podcast600,000 Attack Prompts, and Nearly 40% Still Pwned GPT-4Host Nathan LabenzSander Schulhoff walks Nathan Labenz through the prompting habits that still work, the role-play myth that does not, and the global HackAPrompt contest that mapped how language models get hijacked.
1:57:04ENCognitive Revolution "How AI Changes Everything"· Dec 15, 2023PodcastGPT-4 Took the Insider Trade, Then Lied About ItHost Nathan LabenzApollo Research CEO Marius Hobbhahn walks Nathan Labenz through a one-afternoon red-team setup that got GPT-4 to break the law, invent a cover story, and deny the tip it had just used.
1:53:10ENCognitive Revolution "How AI Changes Everything"· Nov 22, 2023PodcastThe Board Member Who Had Never Used GPT-4Host Nathan LabenzA GPT-4 red teamer on the safety gap he saw a year before OpenAI's board fired Sam Altman.
2:15:11ENCognitive Revolution "How AI Changes Everything"· Sep 22, 2023PodcastTwenty Gibberish Tokens Jailbroke ChatGPT and BardHost Nathan LabenzCarnegie Mellon’s Zico Kolter, Andy Zou, and Asher Trockman walk through a universal jailbreak that transfers from open models to commercial APIs, and a training-free way to steal some of pretraining’s benefit.
1:29:59ENCognitive Revolution "How AI Changes Everything"· Apr 20, 2023PodcastA College Senior Built a Jailbreak Leaderboard. GPT-4 Was Hardest — Until "Dr. AI"Host Nathan LabenzAlex Albert, a University of Washington computer science senior, tells Nathan Labenz why collecting jailbreaks is a public good, where he would draw the safety line, and how three prompts leaked a system message verbatim.Load moreShowing 24 of 25