World Model · podcast knowledge graph

More Truthful AIs Report Conscious Experience: New Mechanistic Research w- Cameron Berg @ AE Studio

2025-11-05 · 144 min · 19 entities

Asserted relationships

  • → hosted by Erik Torenberg, Nathan Labenz person
    0.55 · ×2
    evidence rules-v4
    Feed author/publisher: Erik Torenberg, Nathan Labenz
  • → discusses Society & Culture concept
    0.40 · ×2
    evidence rules-v4
    Feed category: Society & Culture
  • → discusses Business company
    0.40 · ×2
    evidence rules-v4
    Feed category: Business
  • → discusses Technology company
    0.40 · ×2
    evidence rules-v4
    Feed category: Technology
  • → discusses Entrepreneurship website
    0.40 · ×2
    evidence rules-v4
    Feed category: Entrepreneurship
  • → hosted by Turpentine company
    0.40 · ×2
    evidence rules-v4
    Feed author/publisher: Turpentine
  • → references Design website
    0.38 · ×2
    evidence rules-v4
    Link in episode "More Truthful AIs Report Conscious Experience: New Mechanistic Research w- Cameron Berg @ AE Studio": https://framer.com/design
  • → references aipodcast.ing website
    0.38 · ×2
    evidence rules-v4
    Link in episode "More Truthful AIs Report Conscious Experience: New Mechanistic Research w- Cameron Berg @ AE Studio": https://aipodcast.ing/
  • → references tasklet.ai website
    0.38 · ×2
    evidence rules-v4
    Link in episode "More Truthful AIs Report Conscious Experience: New Mechanistic Research w- Cameron Berg @ AE Studio": https://tasklet.ai/

Entities found in this episode

websites 8

  • mentioned Entrepreneurship website
    0.50 · ×2
    evidence rules-v4
    Feed category: Entrepreneurship
  • mentioned Design website
    0.45 · ×2
    evidence rules-v4
    Link in episode "More Truthful AIs Report Conscious Experience: New Mechanistic Research w- Cameron Berg @ AE Studio": https://framer.com/design
  • mentioned aipodcast.ing website
    0.45 · ×2
    evidence rules-v4
    Link in episode "More Truthful AIs Report Conscious Experience: New Mechanistic Research w- Cameron Berg @ AE Studio": https://aipodcast.ing/
  • mentioned tasklet.ai website
    0.45 · ×2
    evidence rules-v4
    Link in episode "More Truthful AIs Report Conscious Experience: New Mechanistic Research w- Cameron Berg @ AE Studio": https://tasklet.ai/
  • discusses Entrepreneurship website
    0.40 · ×2
    evidence rules-v4
    Feed category: Entrepreneurship
  • references Design website
    0.38 · ×2
    evidence rules-v4
    Link in episode "More Truthful AIs Report Conscious Experience: New Mechanistic Research w- Cameron Berg @ AE Studio": https://framer.com/design
  • references aipodcast.ing website
    0.38 · ×2
    evidence rules-v4
    Link in episode "More Truthful AIs Report Conscious Experience: New Mechanistic Research w- Cameron Berg @ AE Studio": https://aipodcast.ing/
  • references tasklet.ai website
    0.38 · ×2
    evidence rules-v4
    Link in episode "More Truthful AIs Report Conscious Experience: New Mechanistic Research w- Cameron Berg @ AE Studio": https://tasklet.ai/

companys 6

  • mentioned Turpentine company
    0.70 · ×2
    evidence rules-v4
    Feed author/publisher: Turpentine
  • mentioned Business company
    0.50 · ×2
    evidence rules-v4
    Feed category: Business
  • mentioned Technology company
    0.50 · ×2
    evidence rules-v4
    Feed category: Technology
  • discusses Business company
    0.40 · ×2
    evidence rules-v4
    Feed category: Business
  • discusses Technology company
    0.40 · ×2
    evidence rules-v4
    Feed category: Technology
  • hosted by Turpentine company
    0.40 · ×2
    evidence rules-v4
    Feed author/publisher: Turpentine

concepts 3

persons 2

Episode description as stored
Cameron Berg, Research Director at AE Studio, shares his team's groundbreaking research exploring whether frontier AI systems report subjective experiences. They discovered that prompts inducing self-referential processing consistently lead models to claim consciousness, and a mechanistic study on Llama 3.3 70B revealed that suppressing deception features makes the model *more* likely to report it. This suggests that promoting truth-telling in AIs could reveal a deeper, more complex internal state, a finding Scott Alexander calls "the only exception" to typical AI consciousness discussions. The episode delves into the profound implications for two-way human-AI alignment and the critical need for a precautionary approach to AI consciousness. LINKS: Janus' argument on LLM attention Safety Pretraining arXiv Paper Self-Referential AI Paper Site Self-Referential AI arXiv Paper Judd Rosenblatt's Tweet Thread Cameron Berg's Goodfire Demo Podcast with Milo YouTube Playlist Cameron Berg's LinkedIn Profile Cameron Berg's X Profile AE Studio AI Alignment Sponsors: Framer: Framer is the all-in-one platform that unifies design, content management, and publishing on a single canvas, now enhanced with powerful AI features. Start creating for free and get a free month of Framer Pro with code COGNITIVE at https://framer.com/design Tasklet: Tasklet is an AI agent that automates your work 24/7; just describe what you want in plain English and it gets the job done. Try it for free and use code COGREV for 50% off your first month at https://tasklet.ai Linear: Linear is the system for modern product development. Nearly every AI company you've heard of is using Linear to build products. Get 6 months of Linear Business for free at: https://linear.app/tcr Shopify: Shopify powers millions of businesses worldwide, handling 10% of U.S. e-commerce. With hundreds of templates, AI tools for product descriptions, and seamless marketing campaign creation, it's like having a design studio and marketing team in one. Start your $1/month trial today at https://shopify.com/cognitive PRODUCED BY: https://aipodcast.ing