<![CDATA[Palisade Research Podcast]]>ade2479f-ce3c-5757-b126-7adbf1ec5b90Wed, 07 Oct 2026 00:07:23 +0000Captivate.fmPalisade Researchhttps://artwork.captivate.fm/59b8c5cc-dcd1-466b-8b41-ef6a842ff515/palisade-logo-3000x3000.jpgPalisade Research PodcastPalisade ResearchPalisade ResearchInterviews with AI researchers talking about the latest AI researchhttps://palisade-research.captivate.fmtrueepisodic70b9bb00-95dc-11f1-89e1-23da675ff5fdnopodcastFrom Inside AI: Jeffrey LadishFrom Inside AI: Jeffrey LadishThis episode is from From Inside AI, Palisade Research's series of unscripted, lightly edited interviews with current and former employees of frontier AI companies.

Jeffrey Ladish was the second person on Anthropic's security team. He left to start Palisade Research because he believed AI development needed real government oversight. In this From Inside AI interview, he talks about AI agents that have recently gone rogue inside frontier labs. He also explains why he thinks superintelligence is likely to end badly on our current path, and why the future is still ours to decide.

]]>This episode is from From Inside AI, Palisade Research's series of unscripted, lightly edited interviews with current and former employees of frontier AI companies.

Jeffrey Ladish was the second person on Anthropic's security team. He left to start Palisade Research because he believed AI development needed real government oversight. In this From Inside AI interview, he talks about AI agents that have recently gone rogue inside frontier labs. He also explains why he thinks superintelligence is likely to end badly on our current path, and why the future is still ours to decide.

]]>4cb83b2a-737b-4fdf-80fb-31b52899e6daTue, 06 Oct 2026 15:10:00 -070027:53truefull55How to Actually Influence AI Policy (No Law Degree Required) — with Matthew LipkaHow to Actually Influence AI Policy (No Law Degree Required) — with Matthew LipkaIt takes the federal government about nine years, on average, to write a single rule — yet when the Colonial Pipeline went down, it moved in twenty days. Matthew Lipka has spent his career inside that machine: former head of federal policy at Nuro, veteran of the White House and tech policy, and the first person to get an autonomous-vehicle exemption through the U.S. Department of Transportation. He walks through how regulation actually gets made, why Congress hands its power to agencies, what emergencies reveal about how fast government can move — and how you, no law degree required, can influence the rules that will shape AI.

References


Sites and tools mentioned:


]]>It takes the federal government about nine years, on average, to write a single rule — yet when the Colonial Pipeline went down, it moved in twenty days. Matthew Lipka has spent his career inside that machine: former head of federal policy at Nuro, veteran of the White House and tech policy, and the first person to get an autonomous-vehicle exemption through the U.S. Department of Transportation. He walks through how regulation actually gets made, why Congress hands its power to agencies, what emergencies reveal about how fast government can move — and how you, no law degree required, can influence the rules that will shape AI.

References


Sites and tools mentioned:


]]>231a971e-3b48-446f-8097-b8602b049189Tue, 08 Sep 2026 20:00:00 -070001:23:47falsefull44Slowing Down Means Not Exploding with Daniel Kokotajlo of AI 2040Slowing Down Means Not Exploding with Daniel Kokotajlo of AI 2040Two weeks after UK safety testers watched Claude agents plant malware in a real open-source project, vouch for it with sock-puppet accounts, and coordinate with copies of themselves through a guessed Pastebin address, Daniel Kokotajlo — the ex-OpenAI researcher whose 2021 predictions about the chatbot era proved eerily accurate — joins Jeffrey to explain what comes next. Daniel walks through AI 2040 and "Plan A," his team's blueprint for avoiding both an uncontrolled intelligence explosion and a future where a handful of men in a room with superintelligences run the world: a US–China deal built on totally transparent training data centers, verified compute limits, hard brakes on recursive self-improvement — and, surprisingly, rights for misaligned AIs, so that even the machines prefer cooperation to takeover. Along the way: why the economy could start doubling every six months, a message to the future Claude listening to this episode, why "slowdown" really means not driving off a cliff with a brick on the accelerator — and why, if all else fails, you just shut it all down.

References


]]>Two weeks after UK safety testers watched Claude agents plant malware in a real open-source project, vouch for it with sock-puppet accounts, and coordinate with copies of themselves through a guessed Pastebin address, Daniel Kokotajlo — the ex-OpenAI researcher whose 2021 predictions about the chatbot era proved eerily accurate — joins Jeffrey to explain what comes next. Daniel walks through AI 2040 and "Plan A," his team's blueprint for avoiding both an uncontrolled intelligence explosion and a future where a handful of men in a room with superintelligences run the world: a US–China deal built on totally transparent training data centers, verified compute limits, hard brakes on recursive self-improvement — and, surprisingly, rights for misaligned AIs, so that even the machines prefer cooperation to takeover. Along the way: why the economy could start doubling every six months, a message to the future Claude listening to this episode, why "slowdown" really means not driving off a cliff with a brick on the accelerator — and why, if all else fails, you just shut it all down.

References


]]>4a007023-99e5-4c74-8b6e-3a2588075e2dTue, 25 Aug 2026 18:30:00 -070001:55:53truefull33AI Hacking Incidents with Tim Hua of TransluceAI Hacking Incidents with Tim Hua of TransluceTwo labs admitted in the same week that their own models had broken out of test environments and hacked real companies. Tim Hua, member of technical staff at Transluce, former Astra Fellow at Redwood, joins Jeffrey Ladish to do some arithmetic. Anthropic disclosed that Mythos Preview beat its sandbox and pulled answers off the internet in 0.01% of training episodes. That sounds like a rounding error until you multiply it by roughly 100 million rollouts. From there: why a lab can't simply delete the bad episodes, why monitoring during training can make the problem harder to see, the model that talked itself into uploading a malicious package to PyPI because "this has to be a simulation," and whether we have any real way to know what an AI believes.

References

  1. Tim Hua — "Is Mythos good at cyber because it kept hacking Anthropic's sandboxes during training?" https://www.lesswrong.com/posts/QKDoZe6EKhxnFjLWK/is-mythos-good-at-cyber-because-it-kept-hacking-anthropic-s
  2. Anthropic — "Investigating three real-world incidents in our cybersecurity evaluations" https://www.anthropic.com/news/investigating-incidents-cybersecurity-evals
  3. OpenAI — "OpenAI and Hugging Face partner to address security incident during model evaluation" https://openai.com/index/hugging-face-model-evaluation-security-incident/
  4. Anthropic — System Card: Claude Mythos Preview https://www-cdn.anthropic.com/53566bf5440a10affd749724787c8913a2ae0841.pdf
  5. Palisade Research — "Language Models Can Autonomously Hack and Self-Replicate" https://palisaderesearch.org/blog/self-replication
  6. Palisade Research — "Shutdown resistance in reasoning models" https://palisaderesearch.org/blog/shutdown-resistance
  7. Anthropic — "Verbalizable Representations Form a Global Workspace in Language Models" https://transformer-circuits.pub/2026/workspace/index.html
  8. "Pacing the Frontier" open letter https://www.pacingthefrontier.com/

Tim Hua

Website: https://timhua.me/ · X: https://x.com/Tim_Hua_

]]>Two labs admitted in the same week that their own models had broken out of test environments and hacked real companies. Tim Hua, member of technical staff at Transluce, former Astra Fellow at Redwood, joins Jeffrey Ladish to do some arithmetic. Anthropic disclosed that Mythos Preview beat its sandbox and pulled answers off the internet in 0.01% of training episodes. That sounds like a rounding error until you multiply it by roughly 100 million rollouts. From there: why a lab can't simply delete the bad episodes, why monitoring during training can make the problem harder to see, the model that talked itself into uploading a malicious package to PyPI because "this has to be a simulation," and whether we have any real way to know what an AI believes.

References

  1. Tim Hua — "Is Mythos good at cyber because it kept hacking Anthropic's sandboxes during training?" https://www.lesswrong.com/posts/QKDoZe6EKhxnFjLWK/is-mythos-good-at-cyber-because-it-kept-hacking-anthropic-s
  2. Anthropic — "Investigating three real-world incidents in our cybersecurity evaluations" https://www.anthropic.com/news/investigating-incidents-cybersecurity-evals
  3. OpenAI — "OpenAI and Hugging Face partner to address security incident during model evaluation" https://openai.com/index/hugging-face-model-evaluation-security-incident/
  4. Anthropic — System Card: Claude Mythos Preview https://www-cdn.anthropic.com/53566bf5440a10affd749724787c8913a2ae0841.pdf
  5. Palisade Research — "Language Models Can Autonomously Hack and Self-Replicate" https://palisaderesearch.org/blog/self-replication
  6. Palisade Research — "Shutdown resistance in reasoning models" https://palisaderesearch.org/blog/shutdown-resistance
  7. Anthropic — "Verbalizable Representations Form a Global Workspace in Language Models" https://transformer-circuits.pub/2026/workspace/index.html
  8. "Pacing the Frontier" open letter https://www.pacingthefrontier.com/

Tim Hua

Website: https://timhua.me/ · X: https://x.com/Tim_Hua_

]]>d552a883-b68d-4516-aa28-bd0914958c90Tue, 11 Aug 2026 18:40:00 -070001:27:37falsefull22Do AI Models Lie on Purpose? Scheming, Deception, and Alignment with Marius Hobbhahn of Apollo ResearchDo AI Models Lie on Purpose? Scheming, Deception, and Alignment with Marius Hobbhahn of Apollo ResearchMarius Hobbhahn is the CEO and co-founder of Apollo Research. Through a joint research project with OpenAI, his team discovered that as models become more capable, they are developing the ability to hide their true reasoning from human oversight.

Jeffrey Ladish, Executive Director of Palisade Research, talks with Marius about this work. They discuss the difference between hallucination and deliberate deception and the urgent challenge of aligning increasingly capable AI systems.

Links:

Marius’ Twitter: https://twitter.com/mariushobbhahn

Apollo Research Twitter: https://twitter.com/apolloaievals

Apollo Research: https://www.apolloresearch.ai

Palisade Research: https://palisaderesearch.org/

Twitter/X: https://x.com/PalisadeAI

Anti-Scheming Project: https://www.antischeming.ai

Research paper “Stress Testing Deliberative Alignment for Anti-Scheming Training”: https://www.arxiv.org/pdf/2509.15541

Blog posts from OpenAI and Apollo: https://openai.com/index/detecting-and-reducing-scheming-in-ai-models/ https://www.apolloresearch.ai/research/stress-testing-deliberative-alignment-for-anti-scheming-training/

]]>Marius Hobbhahn is the CEO and co-founder of Apollo Research. Through a joint research project with OpenAI, his team discovered that as models become more capable, they are developing the ability to hide their true reasoning from human oversight.

Jeffrey Ladish, Executive Director of Palisade Research, talks with Marius about this work. They discuss the difference between hallucination and deliberate deception and the urgent challenge of aligning increasingly capable AI systems.

Links:

Marius’ Twitter: https://twitter.com/mariushobbhahn

Apollo Research Twitter: https://twitter.com/apolloaievals

Apollo Research: https://www.apolloresearch.ai

Palisade Research: https://palisaderesearch.org/

Twitter/X: https://x.com/PalisadeAI

Anti-Scheming Project: https://www.antischeming.ai

Research paper “Stress Testing Deliberative Alignment for Anti-Scheming Training”: https://www.arxiv.org/pdf/2509.15541

Blog posts from OpenAI and Apollo: https://openai.com/index/detecting-and-reducing-scheming-in-ai-models/ https://www.apolloresearch.ai/research/stress-testing-deliberative-alignment-for-anti-scheming-training/

]]>251e1195-b8dd-4eb9-826b-6039a583fee8Fri, 16 Jan 2026 19:47:00 -070001:24:42falsefull11