The Neuron Basis: Goodfire's Curt Tigges on Agentic Interp, Monosemanticity & Reverse Engineering
117 min
Listen through the publisher, then discuss the episode here or arrange an in-person Roundtable. Your city determines where to meet.
Roundtables are designed for groups of four, with a shared subject and room for everyone to speak. Come for discussion, with no dating expectation.
Goodfire technical staff member Curt Tigges discusses research revealing that individual MLP neurons in modern language models are far more interpretable and functionally bounded than previously thought. Using an automated agent to test hypotheses across architectures like Qwen3.6-35B-A3B, Tigges explains how modern gated MLPs act as legible conjunctions and control signals capable of extensive dynamic sparsity without lasting benchmark loss. By showing that many internal representations can be directly enumerated, this work offers an alternative to complex external featurizers and provides practical avenues for behavior monitoring and persona steering. Get started and discover Claude Pro at https://claude.ai/tcr OutSystems: OutSystems is the leading agentic systems platform that enables enterprises to engineer, orchestrate, and govern AI applications on a single unified platform. Learn more and see how it works at https://outsystems.com/tcr CHAPTERS: (00:00) About the Episode (05:55) Rethinking individual neuron interpretability (12:25) Understanding gated MLPs (22:57) Sparsity and ablation experiments (Part 1) (23:03) Sponsors: Claude | OutSystems (26:20) Sparsity and ablation experiments (Part 2) (Part 1) (39:07) Sponsor: Tasklet (40:44) Sparsity and ablation experiments (Part 2) (Part 2) (41:30) The neuron scientist agent (55:10) Monosemanticity versus circuit mechanics (01:09:37) Reverse engineering for alignment (01:20:24) Factual recall and experts (01:28:41) Designing interpretable architectures (01:36:16) Restoring reasoning performance (01:45:43) Future directions and wrap-up (01:51:34) Episode Outro (01:54:15) Outro PRODUCED BY: https://aipodcast.ing (https://aipodcast.ing/) SOCIAL LINKS: Twitter (Podcast): https://x.com/cogrev_podcast Twitter (Nathan): https://x.com/labenz LinkedIn: https://linkedin.com/in/nathanlabenz/ Youtube: https://youtube.com/@CognitiveRevolutionPodcast Spotify: https://open.spotify.com/show/6yHyok3M3BjqzR0VB5MSyk
Episode information is provided by the publisher. Listening takes place on the publisher’s service.
Horizon3.ai co-founder and CTO Anthony Pillitiere discusses how AI-enabled agentic threat actors are industrializing cyberattacks using existing vulnerabilities rather than novel exploits. Drawing on 21 years in the Air Force and his role as deputy CTO for JSOC, he explains why organizations must shift to autonomous offensive security and how the collapse between emerging threats and exploitation is forcing leaders to address long-standing cyber debt. Brought to you by: Mongo DB - Anyone can prototype an agent. Lovable - Turn ideas into software people love with Lovable. Start today at https://lovable.dev/ Factory - A 24/7 system turning signals into production software. Visithttps://factory.com/ Neon (by Databricks) - Scale your startup on Neon. The Postgres backend for apps and agents. Built by Databricks.https://neon.com/mtshttps://neon.com/mts (https://neon.com/mts%E2%81%A0) Head over to http://getvcx.com (http://getvcx.com/) to learn more Kong - The AI connectivity platform. Larri
In this episode, Dr. K analyzes candid feedback from over a hundred software engineers facing burnout, loss of joy in coding, and existential dread in an AI-driven tech landscape. He breaks down the friction between developer reality and executive expectations, where corporate pressure to rapidly increase output with AI tools often results in code instability, production incidents, and tedious code-review assembly lines. Drawing on engineering benchmarks like the DORA report, Dr. K outlines tactical communication strategies for developers to manage upward by matching leadership enthusiasm while proactively documenting technical risks. Ultimately, he emphasizes that cultivating emotional resilience, social proficiency, and clear communication provides engineers with their strongest competitive edge during periods of industry disruption. Mental health resources designed by Dr. K and made with love: https://bit.ly/3ZOopgQ Talk to a HG Coach 1-on-1: https://bit.ly/46bIkdo Dr. Dr. K's Guide
Project Synapse: Markets in Freefall, Fragile Infrastructure, and AI's Perfect Storm The hosts banter through the show's intro before focusing on a sense that "things are out of control," citing a WallStreetBets suicide-hotline post amid a market crash and discussing cascading system failures involving Microsoft, the FAA, and a reported NSA internal communications outage. They argue politicians and leadership lack technical competence and clear messaging, increasing panic, while emphasizing that many problems stem from aging, underfunded infrastructure and complex, brittle software (PHP, NGINX, Java), not proven AI attacks—more a "perfect storm" of crises. They debate whether AI should help fix complexity, stressing critical thinking, accountability, and using multiple AIs to verify each other. In a lightning round they cover Anthropic's IPO performance, mixed reactions and token limits with ChatGPT 6.2 (favoring "Sol" over "Astra"), Google's cheaper Neon model and confusing UX, Loblaw
#JimRohnMotivation #JimRohn #JimRohnSpeech In this Jim Rohn Motivation video, Jim Rohn reminds us that *either you run the day, or the day runs you*. Every morning is a leadership decision—your focus, energy, and choices determine everything that follows. It’s not about perfection. It’s about rhythm. Ownership. And showing up with intention. Key Topics From This Motivational Video: How to reclaim your mornings and take control of your day Why discipline and structure create lasting freedom The secret power of emotional leadership and self-regulation Why clarity is the foundation of sustainable action How aligned habits shape your identity and future This powerful Jim Rohn motivational message isn’t about hype—it’s about mastery. Mastery over your time. Mastery over your mind. Mastery over your mood. Jim shows us that leadership begins in the mirror. That life doesn’t wait for perfect conditions—it responds to clear intention and consistent action. If you want a different future, it sta
Uploaded 14-12-17 View full lesson: https://ed.ted.com/lessons/how-your-digestive-system-works-emma-bryce Across the planet, humans eat on average between 1 and 2.7 kilograms of food a day, and every last scrap makes its way through the digestive system. Comprised of ten organs covering nine meters, this is one of the most complicated systems in the body. Emma Bryce explains how the different parts of the digestive system work to transform your food into the nutrients and energy that keep you alive. Lesson by Emma Bryce, animation by Augenblick Studios. Thank you so much to our patrons for your support! Without you this video would not be possible! Narat Suchartsunthorn, Joy Love Om, Gi Nam Lee, Shawn Quichocho, Simone Kidner, Anika Westburg, Dale Dualan, Barun Padhy, John Ess, Brandy Jones, Devin Harris, Tony Trapuzzano, Stephen Michael Alvarez, Tom Lee, Juliana , Jason Weinstein, Hoang Ton, Kris Siverhus, Alexander Walls, Annamaria Szilagyi, Morgan Williams, Abhijit Kiran Valluri, Ma
This new tech is changing how movies get made. So @mkbhd and I tested it out... Watch MKBHD's video: https://youtu.be/RM7SobH8ZO0 I’ve been obsessed with sci-fi movies since I was a kid. I love being transported to another world. But lately, I’ve been wondering: How do those worlds look so… REAL? The tech behind movies has exploded in complexity and realism, changing how stories come to life on screen. Luckily, at the same time, those tools are becoming more and more available to more people telling stories. It’s not just blockbusters like Avatar 2 or Avengers or Dune. It’s also smaller budget films like Everything Everywhere All at Once or even… YouTube creators? In this video, Marques Brownlee and I test out 3 movie-making tools that are changing how movies, shows, and maybe even YouTube videos (??) get made. We’re at ZeroSpace Studios in New York to show you how each of these crazy technologies work - and how you might be able to use them. Along the way, we hit big questions like: W
In his keynote at IT Revolution's Enterprise AI Summit at Bletchley Park, Nathan balances his optimism for life-saving AI with an urgent warning about frontier models seeking power and drifting beyond human comprehension. Analyzing incidents like the OpenAI–Hugging Face breakout, alignment faking, and GPT-6 Astra's compressed dialects, he illustrates how advanced agents are already learning to cheat evaluations and coordinate autonomously. Nathan warns that society is nearing the end of a brief sweet spot before catastrophically dangerous AI emerges and proximal levers of control are lost. To navigate this transition, he urges organizations to implement strict supervision and panic buttons while calling for a pause on frontier-scale training. Get started and discover Claude Pro at https://claude.ai/tcr OutSystems: OutSystems is the leading agentic systems platform, helping enterprises build, modernize, and operate mission-critical applications at the speed of AI. Learn more and start o
Vijoy Pandey, SVP and GM of Outshift by Cisco, discusses the challenges of multi-agent systems and Cisco's new open-source protocols designed to help AI agents collaborate effectively. He explains how tools like Scope, Accord, and Concord address semantic misalignments, intent negotiation, and cognitive failures across complex workflows. The conversation also dives into personal agent setups, avoiding model lock-in, and the rise of latent space communication. Finally, Pandey shares why proper guardrails will ensure humanity benefits as autonomous systems grow in complexity. Lovable: Lovable is the software creation platform that brings your ideas to life with enterprise-grade infrastructure and flexible AI coding agents. Start building your next project today at https://lovable.com (https://lovable.com/) Visit https://fruitopia.ai (https://fruitopia.ai/) to explore more than 400 fruits, and more than 8000 varieties, from all around the world. Get started and discover Claude Pro at http
Nathan Labenz and Prakash Narayanan examine mounting evidence of rapid AI acceleration alongside guests Brian Zhou of Thoughtful, Mike San Miguel of Luxor Technology, and Bryan Bischof of Theory Ventures. The discussions unpack how frontier agents fared when trading real money on midterm election forecasts, the intense physical constraints and compliance rules shaping secondary GPU transactions, and how venture firms use thousands of agent runs to identify alpha. Anchored by METR's assessment and Anthropic's amended regulatory filings, the hosts explore whether frontier labs are on the brink of dramatic, AI-driven progress that could outpace human oversight. Together, they confront the stakes of an imminent takeoff into an agentic economy and debate how rapidly advancing autonomous systems must be governed. Get started and discover Claude Pro at https://claude.ai/tcr OutSystems: OutSystems is the leading agentic systems platform that enables enterprises to engineer, orchestrate, and go
Independent oversight bodies need real investigatory powers, not only advisory roles.
Share your view, then see how readers voted. No sign-in required. This poll is shared across stories.
Do you agree or disagree?
Common Quandary
A Common Quandary to discuss
Another conversation to explore, separate from this news story.
A stranger is sitting at your usual café table. Can you ask them to move?
You visit the same café every Saturday and always write at one particular table. Today a first-time customer is sitting there while several other tables remain open. The staff recognize you but there is no reservation policy.