Show Notes
Take a trip with me through the paper Large Language Models, A Survey, published on February 9th of 2024. All figures and tables mentioned throughout the episode can be found on the Into AI Safety podcast website. 00:36 - Intro and authors 01:50 - My takes and paper structure 04:40 - Getting to LLMs 07:27 - Defining LLMs & emergence 12:12 - Overview of PLMs 15:00 - How LLMs are built 18:52 - Limitations if LLMs 23:06 - Uses of LLMs 25:16 - Evaluations and Benchmarks 28:11 - Challenges and future directions 29:21 - Recap & outro Links to all articles/papers which are mentioned throughout the episode can be found below, in order of their appearance. Large Language Models, A Survey Meysam's LinkedIn Post Claude E. ShannonA symbolic analysis of relay and switching circuits (Master's Thesis) Communication theory of secrecy systems A mathematical theory of communication Prediction and entropy of printed English Future ML Systems Will Be Qualitatively Different More Is Different Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training Are Emergent Abilities of Large Language Models a Mirage? Are Emergent Abilities of Large Language Models just In-Context Learning? Attention is all you need Direct Preference Optimization: Your Language Model is Secretly a Reward Model KTO: Model Alignment as Prospect Theoretic Optimization Optimization by Simulated Annealing Memory and new controls for ChatGPT Hallucinations and related concepts—their conceptual background
More from Into AI Safety
Etienne Brisson and Allan Brooks, founder and program director of The Human Line Project, sat down with me to talk about AI-induced psychological harm, starting with their own experiences. Allan spent a month spiraling with ChatGPT, ending with him warning national security agencies about an encryption break that never happened. Etienne's uncle became convinced his chatbot was sentient and was hospitalized still messaging it from the back of a police car.
Dr. Evan Miyazono joins Jacob to talk about his path from quantum networking and Protocol Labs to founding Atlas Computing. They discuss why Atlas moved away from formal methods research and toward what Evan calls “field strategy”: identifying important problems, figuring out what interventions could actually address them, and finding the people best positioned to make them happen. The conversation also covers the resilience gap map, coordination failures, AI safety, "value alignment," and the question of how to decide what work is worth doing when there’s no obvious organization responsible for it. Check out the video version of this podcast on the Kairos.fm YouTube channel, or the extended version on Patreon! Chapters
What if the safest AI models weren't built by adding guardrails after training, but by shaping what gets learned in the first place? Ethan Roland, senior alignment researcher at AE Studio and first author on an ICML 2026 spotlight paper, joins Jacob to talk about gradient routing, a technique that routes dangerous capabilities into isolated parts of a model's architecture where they can be locked or removed entirely. They get into the absorption effect, KYC-style access control frameworks, and what it would actually take for frontier labs to adopt this kind of work before it's needed rather than after. Chapters
Today's episode does double duty as an interview and an announcement. Joe Williams, host of the new Kairos.fm show "Beyond the Paycheck: Reclaiming the Case for UBI in the Age of AI," joins Jacob to talk about his background as a freelance translator and how AI quietly dismantled his livelihood in 2025. From there the conversation expands into whether this moment is really different from past waves of automation, who exactly makes up the tech billionaire class, and why you should probably raise an eyebrow when someone like Elon Musk says he supports UBI. Go check out Reclaiming UBI! Chapters
Zainab Majid, co-founder of Asymmetric Security, joins Jacob for a conversation on the intersection between AI Safety and cybersecurity, as well as the future of digital forensics. Drawing from years of incident response work, she explains how cyber attacks actually unfold, why AI is changing both offense and defense, and how her team is building AI-native tools to investigate breaches faster and more effectively. Other topics explored in this episode include trust in the AI/cybersecurity industries, the realities behind cybersecurity hype, and the challenge of keeping humans meaningfully involved as these systems become more capable. Zainab also gives practical, actionable advice on how you can protect yourself. If you're interested in over 30 minutes of additional content, head on over to the Kairos.fm Patreon where you can become a subscriber for just $2 per month, which helps make this whole podcasting thing a bit more sustainable. Chapters