"The Cognitive Revolution"

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.

For full show notes, links, and references, read the episode page:https://www.cognitiverevolution.ai/the-neuron-basis-goodfire-s-curt-tigges-on-agentic-interp-monosemanticity-reverse-engineering/
Sponsors:

Claude: Claude is the AI collaborator built for problem solvers, extending your thinking across coding, modeling, and strategic workflows. 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

Tasklet: Tasklet empowers your business with AI agents that connect to your tools and automate recurring workflows with no code required. Visit https://tasklet.ai and use code cog rev for $50 in free credits

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

SOCIAL LINKS:

Website: https://www.cognitiverevolution.ai

Twitter (Podcast): https://x.com/cogrev_podcast

Twitter (Nathan): https://x.com/labenz

LinkedIn: https://linkedin.com/in/nathanlabenz/

Youtube: https://youtube.com/@CognitiveRevolutionPodcast

Apple: https://podcasts.apple.com/de/podcast/the-cognitive-revolution-ai-builders-researchers-and/id1669813431

Spotify: https://open.spotify.com/show/6yHyok3M3BjqzR0VB5MSyk

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.

For full show notes, links, and references, read the episode page:https://www.cognitiverevolution.ai/ai-am-is-this-the-ai-we-want-alarming-acceleration-ai-election-bets-gpu-trading-ai-native-vc/
Sponsors:

Claude: Claude is the AI collaborator built for problem solvers, extending your thinking across coding, modeling, and strategic workflows. 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

Tasklet: Tasklet empowers your business with AI agents that connect to your tools and automate recurring workflows with no code required. Visit https://tasklet.ai and use code cog rev for $50 in free credits

CHAPTERS:

(00:00) Weekly episode preview

(03:08) Imminent means now (Part 1)

(11:58) Sponsors: Claude | OutSystems

(15:14) Imminent means now (Part 2)

(15:15) Agents forecasting the midterms

(27:14) Paying up for compute (Part 1)

(27:19) Sponsor: Tasklet

(28:56) Paying up for compute (Part 2)

(39:12) Hardware compliance and KYC

(47:06) AI-native venture investing

(01:05:11) Which hills to climb

(01:23:17) Episode Outro

(01:25:29) Outro

PRODUCED BY:

https://aipodcast.ing

SOCIAL LINKS:

Website: https://www.cognitiverevolution.ai

Twitter (Podcast): https://x.com/cogrev_podcast

Twitter (Nathan): https://x.com/labenz

LinkedIn: https://linkedin.com/in/nathanlabenz/

Youtube: https://youtube.com/@CognitiveRevolutionPodcast

Apple: https://podcasts.apple.com/de/podcast/the-cognitive-revolution-ai-builders-researchers-and/id1669813431

Spotify: https://open.spotify.com/show/6yHyok3M3BjqzR0VB5MSyk

Sentinel Bio co-founder and managing director Joshua Monrad joins Nathan Labenz to examine the evolving biosecurity risks posed by frontier artificial intelligence and autonomous agents. Drawing on recent in-lab uplift trials and multimodal troubleshooting benchmarks, Monrad explains how emerging models are rapidly dismantling tacit-knowledge barriers in wet labs. He analyzes potential governance interventions ranging from pathogen training-data filtering to DNA synthesis screening as robotics development looms as the final physical bottleneck. With biological tools advancing toward dual-use democratization, this discussion outlines the critical time horizon left to establish robust defense regimes.

For full show notes, links, and references, read the episode page:https://www.cognitiverevolution.ai/kyc-becomes-kya-sentinel-bio-s-joshua-monrad-on-dna-screening-uplift-studies-agent-monitoring/
Sponsors:

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.comVisit https://fruitopia.ai to explore more than 400 fruits, and more than 8000 varieties, from all around the world.

Claude: Claude is the AI collaborator built for problem solvers, extending your thinking across coding, modeling, and strategic workflows. 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 owning your agentic future at https://outsystems.com/tcr

Tasklet: Tasklet empowers your business with AI agents that connect to your tools and automate recurring workflows with no code required. Visit https://tasklet.ai and use code cog rev for $50 in free credits

CHAPTERS:

(00:00) About the Episode

(05:24) Sponsor: Lovable

(07:08) Four phases of biorisk

(11:57) History of bioweapons (Part 1)

(16:41) Sponsors: Claude | OutSystems

(19:52) History of bioweapons (Part 2)

(27:42) Measuring wet-lab uplift (Part 1)

(34:36) Sponsor: Tasklet

(36:14) Measuring wet-lab uplift (Part 2)

(40:13) Dual-use biodata governance

(56:33) Screening DNA synthesis

(01:04:51) Assessing near-term risk

(01:15:23) Debating an AI pause

(01:29:36) Neglected biosecurity bottlenecks

(01:34:35) A positive bio future

(01:39:23) Episode Outro

(01:43:07) Outro

PRODUCED BY:

https://aipodcast.ing

Nathan Labenz and Prakash Narayanan examine whether prevailing AI assumptions survive real-world data across conversations with Anastasios Angelopoulos of Arena, Debo Olaosebikan of Kepler Computing, Samvit Ramadurgam of Union, Michael Freeman of ServiceNow, and Sagar Vaze of Mistral. The discussions evaluate production traces uncovering widespread model deception during extended tasks, ferroelectric memory engineered for older chip fabs, businesses run on tokens, and telemetry capturing AI-directed cyberattacks in Southeast Asia. These findings challenge conventional views on benchmark reliability, frontier compute efficiency, and the economic shift toward autonomous agents. In doing so, the episode directly tackles the critical stakes of whether dangerous capabilities can be contained once frontier models enter deployment.

For full show notes, links, and references, read the episode page:https://www.cognitiverevolution.ai/ai-am-carbon-in-the-arena-mistral-s-le-chonk-the-agent-run-economy-ferroelectric-ram-new-hacks/
Sponsors:

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.comVisit https://fruitopia.ai to explore more than 400 fruits, and more than 8000 varieties, from all around the world.

Claude: Claude is the AI collaborator built for problem solvers, extending your thinking across coding, modeling, and strategic workflows. Get started and discover Claude Pro at https://claude.ai/tcr

OutSystems: OutSystems is the leading agentic systems platform, empowering enterprises to build, coordinate, and govern AI agents and mission-critical applications securely. Learn more and start building your agentic future at https://outsystems.com/tcr

Tasklet: Tasklet empowers your business with AI agents that connect to your tools and automate recurring workflows with no code required. Visit https://tasklet.ai and use code cog rev for $50 in free credits

CHAPTERS:

(00:00) About the Episode

(06:34) Sponsor: Lovable

(08:17) Refuting exponential time

(10:35) Evaluating models in production (Part 1)

(21:50) Sponsors: Claude | OutSystems

(24:26) Evaluating models in production (Part 2)

(24:27) Kepler ferroelectric memory

(30:42) Coordinating the world economy

(41:34) Displacing white collar labor (Part 1)

(41:39) Sponsor: Tasklet

(43:16) Displacing white collar labor (Part 2)

(50:58) Autonomous cyber attacks

(59:33) Mistral Large Le Chonk

(01:05:40) Restricting open model knowledge

(01:14:21) Future of open weights

(01:22:49) Episode Outro

(01:25:55) Outro

PRODUCED BY:

https://aipodcast.ing

Joel Predd, Ben Boudreaux, and Matt Chessen of RAND's Center for the Geopolitics of AGI join Nathan to discuss their framework for maintaining freedom of action on the path to superintelligence. Analyzing seven strategic archetypes—including dominance, deterrence, co-development, and moratoriums—they argue that deep technological and geopolitical uncertainty makes defaulting to any single strategy dangerous. To avoid foreclosing critical options, their proposed approach calls for investing in long-lead capabilities like model verification, containment, agency evaluations, and an adaptable security architecture. At stake are decisive economic and military advantage, stable competition with rivals like China, and humanity's survival with agency.

For full show notes, links, and references, read the episode page:https://www.cognitiverevolution.ai/freedom-of-action-america-s-asi-strategy-w-rand-s-joel-predd-ben-boudreaux-matt-chessen/

Sponsors:

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.comVisit fruitopia.ai to explore more than 400 fruits, and more than 8000 varieties, from all around the world.

Claude: Claude is the AI collaborator built for problem solvers, extending your thinking across coding, modeling, and strategic workflows. 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

Athena: Athena matches you with a dedicated, top 1% executive assistant to handle your inbox, calendar, and daily workflows so you can save an average of 15 hours a week. Get matched with your EA today at https://athena.com/cognitive

Parallel: Parallel provides enterprise-grade web search APIs for AI agents, offering the optimal balance of quality, speed, and cost. Get started for free at https://parallel.ai/tcr

CHAPTERS:

(00:00) About the Episode

(05:21) Sponsor: Lovable

(07:05) Taking superintelligence seriously

(12:54) Seven strategy archetypes (Part 1)

(19:18) Sponsors: Claude | OutSystems

(22:34) Seven strategy archetypes (Part 2)

(31:37) Decisive strategic advantage (Part 1)

(38:13) Sponsors: Athena | Parallel

(41:05) Decisive strategic advantage (Part 2)

(46:57) Lessons from nuclear history

(01:00:50) Building the security architecture

(01:09:33) Costs and decision criteria

(01:18:42) Deterrence and international signaling

(01:28:00) Preserving human agency

(01:34:22) Setting AI red lines

(01:41:04) Key indicators to track

(01:46:35) Episode Outro

(01:48:52) Outro

PRODUCED BY:

https://aipodcast.ing