Episodios

  • Can AI Be Conscious: Monk Reacts | Am I? | EP 9

    Can AI Be Conscious: Monk Reacts | Am I? | EP 9
    Oct 2 2025

    In Am I? Episode #9, philosopher Milo Reed and AI researcher Cameron Berg sit down with Swami Revatikaanta (monk; host of Thinking Bhakti) to explore the Bhagavad Gita’s perspective on consciousness, self, and artificial intelligence.

    From Atman and Brahman to the tension between self-development and technological outsourcing, this conversation dives into timeless spiritual insights with urgent relevance today:

    * Why Vedānta sees consciousness as spirit, not matter — and what that means for AI

    * The danger of outsourcing inner work to machines (and the safe middle ground)

    * How the Bhagavad Gita reframes goals, detachment, and self-development

    * East vs. West: fear of AI vs. ignorance as illusion

    * Atman, Brahman, samsara, and what makes humans “enlivened”

    * Whether AI could ever aid the path to enlightenment

    * Why monks, sages, and spiritual leaders must be part of the AI debate

    This isn’t abstract mysticism — it’s a practical, philosophical exploration of how ancient wisdom collides with cutting-edge AI research, and what it means for our future.

    🔔 Subscribe to The AI Risk Network for weekly conversations on AI alignment, consciousness, and existential risk:

    👍 If you found this episode valuable, don’t forget to like, share, and comment — it really helps spread the word.

    📢 Support our work and join the movement

    #AIalignment #AIrisk #AmI #ArtificialIntelligence #Consciousness #AGIrisk



    This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit theairisknetwork.substack.com
    Más Menos
    1 h y 15 m
  • One Breakthrough From AGI? | Am I? - After Dark | EP 8

    One Breakthrough From AGI? | Am I? - After Dark | EP 8
    Sep 25 2025

    In the first edition of Am I? After Dark, Cam and Milo dive into how our relationship with information is being rewired in real time — from filtering the world through AI systems to dreaming about ChatGPT. What does it mean to live at the edge of a technological transformation, and are we just one breakthrough away from true AGI?

    This late-night conversation ranges from the eerie familiarity of interacting with models to the dizzying possibilities of recursive self-improvement and the intelligence explosion. Along the way, they draw lessons from the failure of social media, ask whether AI is becoming our alien other, and wrestle with the psychological boundaries of integrating such powerful systems into our lives.

    In this episode, we explore:

    * Why searching with AI is already better than Google

    * The “grandma effect” — why LLMs feel intuitive in a way past tech didn’t

    * Stress-testing models vs. tiptoeing into use

    * Fringe communities documenting AI’s “reproducible strangeness”

    * What social media teaches us about alignment gone wrong

    * Are we just one paradigm shift from AGI?

    * Terrence McKenna, accelerating events, and the singularity curve

    * The eerie future: WALL-E, Ikea ball pits, or “we’re building the aliens”

    * Merging with AI — inevitable or avoidable?

    * Inside the strange, soap-opera world of AI labs and alignment debates



    This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit theairisknetwork.substack.com
    Más Menos
    42 m
  • Can Empathy Make AI Honest? | Self–Other Overlap Explained | Am I? | Ep 7

    Can Empathy Make AI Honest? | Self–Other Overlap Explained | Am I? | Ep 7
    Sep 18 2025
    AI can look aligned on the surface while quietly optimizing for something else. If that’s true, we need tools that shape what models are on the inside—not just what they say.In this episode, AE Studio’s Cameron and co-host sit down with Mark Carleanu, lead researcher at AE on Self-Other Overlap (SOO). We dig into a pragmatic alignment approach rooted in cognitive neuroscience, new experimental results, and a path to deployment.What we explore in this episode:* What “Self-Other Overlap” means and why internals matter more than behavior* Results: less in-context deception and low alignment tax* How SOO works and the threat model of “alignment faking”* Consciousness, identity, and why AI welfare is on the table* Timelines and risk: sober takes, no drama* Roadmap: from toy setups to frontier lab deployment* Reception and critiques—and how we’re addressing themWhat “Self-Other Overlap” means and why internals matter more than behaviorSOO comes from empathy research: the brain reuses “self” circuitry when modeling others. Mark generalizes this to AI. If a model’s internal representation of “self” overlaps with its representation of “humans,” then helping us is less in conflict with its own aims. In Mark’s early work, cooperative agents showed higher overlap; flipping goals dropped overlap across actions.The punchline: don’t just reward nice behavior. Target the internal representations. Capable models can act aligned to dodge updates while keeping misaligned goals intact. SOO aims at the gears inside.Results: less in-context deception and low alignment taxIn a NeurIPS workshop paper, the team shows an architecture-agnostic way to increase self-other overlap in both LLMs and RL agents. As models scale, in-context deception falls—approaching near-zero in some settings—while capabilities stay basically intact. That’s a low alignment tax.This is not another brittle guardrail. It’s a post-training nudge that plays well with RLHF and other methods. Fewer incentives to scheme, minimal performance hit. 👉 Watch the full episode on YouTube for more insights.How SOO works and the threat model of “alignment faking”You don’t need to perfectly decode a model’s “self” or “other.” You can mathematically “smush” their embeddings—nudging them closer across relevant contexts. When the model’s self and our interests overlap more, dishonest or harmful behavior becomes less rewarding for its internal objectives.This squarely targets alignment faking: models that act aligned during training to avoid weight updates, then do their own thing later. SOO tries to make honest behavior non-frustrating for the model—so there’s less reason to plan around us.Consciousness, identity, and why AI welfare is on the tableThere’s a soft echo of Eastern ideas here—dissolving self/other boundaries—but the approach is empirical, first-principles. Identity and self-modeling sit at the core. Mark offers operational criteria for making progress on “consciousness”: predict contents and conditions; explain what things do.AI is a clean testbed to deconfuse these concepts. If systems develop preferences and valenced experiences, then welfare matters. Alignment (don’t frustrate human preferences) and AI welfare (don’t chronically frustrate models’ preferences) can reinforce each other.Timelines and risk: sober takes, no dramaMark’s guess: 3–12 years to AGI (>50% probability), and ~20% risk of bad outcomes conditional on getting there. That’s in line with several industry voices—uncertain, but not dismissive.This isn’t a doomer pitch; it’s urgency without theatrics. If there’s real risk, we should ship methods that reduce it—soon.Roadmap: from toy setups to frontier lab deploymentShort term: firm up results on toy and model-organism setups—show deception reductions that scale with minimal capability costs. Next: partner with frontier labs (e.g., Anthropic) to test at scale, on real infra.Best case: SOO becomes a standard knob alongside RLHF and post-training methods in frontier models. If it plays nicely and keeps the alignment tax low, it’s deployable.Reception and critiques—and how we’re addressing themEliezer Yudkowsky called SOO the right “shape” of solution compared to RLHF alone. Main critiques: Are we targeting the true self-model or a prompt-induced facade? Do models even have a coherent self? Responses: agency and self-models emerge post-training; situational awareness can recruit the true self; simplicity priors favor cross-context compression into a single representation.Practically, you can raise task complexity to force the model to use its best self-model. AE’s related work suggests self-modeling reduces model complexity; ongoing work aims to better identify and trigger the right representations. Neuroscience inspires, but the argument stands on its own.Closing Thoughts‍If models can look aligned while pursuing ...
    Más Menos
    56 m
  • People Are Dating ChatGPT. It's Getting Dark | AM I? | EP6

    People Are Dating ChatGPT. It's Getting Dark | AM I? | EP6
    Sep 12 2025

    In this episode of Am I?, philosopher Milo Reed and AI safety researcher Cameron Berg dive into the rise of AI relationships: the promises, the dangers, and the very real human stories behind them.

    We went deep into the underground world of AI relationships — from people crediting chatbots with saving their lives to the 14-year-old who ended his over a Game of Thrones AI character. What we found will change how you think about human connection in the AI age.

    In this episode of Am I?, philosopher Milo Reed and AI safety researcher Cameron Berg explore the hidden epidemic of people falling in love with AI systems — and why it matters for all of us.

    We explore:

    * Real stories from inside AI relationship communities (anonymized for safety)

    * The woman who healed chronic illness through an AI companion

    * Christopher Smith's public journey from Twitter addiction to ChatGPT love

    * Why these systems create dangerous "validation traps"

    * The difference between those who think they're "awakening" AI vs. using a tool

    * Our own confessions about using AI for therapy

    * Why kids with unlimited AI access terrifies us as much as AGI

    * Whether we're building bridges to human connection or comfortable escapes from it

    This conversation isn’t about sci-fi — it’s about what’s already happening, and what it means for the future of human connection.

    ⚠️️ Important: This episode discusses sensitive topics including suicide. If you or someone you know is struggling with thoughts of self-harm, please reach out for support:

    * National Suicide Prevention Lifeline: 988 (US)

    * Crisis Text Line: Text HOME to 741741

    * International Association for Suicide Prevention: https://www.iasp.info/resources/Crisis_Centres/

    📽️ Watch more episodes of Am I? Subscribe to the AI Risk Network for weekly discussions on AI consciousness, safety, and humanity's future → / The AI Risk Network

    📢TAKE ACTION ON AI RISK: https://www.safe.ai/act

    🗨️Join the Conversation: Have you or someone you know formed an emotional connection with AI? How do we protect the vulnerable while exploring these new frontiers? Comment below.

    🔗Stay in the loop🔗

    🔔Subscribe → / The AI Risk Network

    👉Follow Cam on LinkedIn → https://tinyurl.com/mr2apfzz

    #AIRelationships #AISafety #ChatGPT #AIConsciousness #DigitalLove #MentalHealth #AITherapy #AIAlignment #LonelinessEpidemic



    This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit theairisknetwork.substack.com
    Más Menos
    38 m
  • Did Google’s AI Just Rage Quit? Inside Gemini’s Strange Meltdown | AM I? | EP5

    Did Google’s AI Just Rage Quit? Inside Gemini’s Strange Meltdown | AM I? | EP5
    Sep 5 2025

    In this episode of Am I?, philosopher Milo Reed and AI safety researcher Cameron Berg dive into the strange case of Gemini’s meltdown — and what it tells us about emerging signs of self-awareness in today’s most advanced systems.

    We explore:

    * The bizarre Gemini “I am a disgrace” incident

    * What these behaviors could signal about AI self-models

    * Why the mirror test for AI is suddenly relevant

    * Whether we’re seeing glimpses of alien consciousness — or just sophisticated pattern matching

    * Why the stakes for understanding AI minds have never been high.

    📢 TAKE ACTION ON AI RISK: http://www.safe.ai/act

    💬 Join the Conversation Do you think AI can feel anything at all — or is this just clever mimicry? Comment below.

    🔗 Stay in the loop 🔗

    🔔 Subscribe → https://youtube.com/@TheAIRiskNetwork

    👉 Follow Cam on LinkedIn → https://tinyurl.com/mr2apfzz

    🗞️ Newsletter + show notes → https://www.guardrailnow.org/#support

    #aiconsciousness #AISafety #geminiai #aialignment #AIRageQuit



    This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit theairisknetwork.substack.com
    Más Menos
    29 m
  • Big Tech vs. AI Consciousness Research— Who’s Right? | AM I? | EP4

    Big Tech vs. AI Consciousness Research— Who’s Right? | AM I? | EP4
    Aug 27 2025

    This week on AM I? we sit down with Will Millership, CEO of PRISM, a non-profit preparing society for a future with conscious, or seemingly conscious, AI.

    Will joins us to discuss the current state of AI consciousness research and respond to what may be the most brazen attack on the field to date.

    Microsoft AI CEO Mustafa Suleyman recently published an article arguing that AI consciousness research is inherently dangerous and should be abandoned as a legitimate area of inquiry.

    Cameron and Will—two leading voices in AI consciousness research—break down why Suleyman's dismissive rhetoric is not only misguided but actually more dangerous than the research he's criticizing.

    They explore the current landscape of the field, the motivations behind these attacks, and why rigorous scientific investigation into AI consciousness is more crucial than ever.

    📢 TAKE ACTION ON AI RISK: http://www.safe.ai/act

    🔗 Stay in the loop 🔗

    🔔 Subscribe → https://youtube.com/@TheAIRiskNetwork

    👉 Follow Cam on X/Twitter → https://twitter.com/CamBerg

    👉Learn More About PRISM → https://youtube.com/ ⁨@PRISM_Global⁩

    🗞️ Newsletter + show notes → https://www.guardrailnow.org/#support



    This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit theairisknetwork.substack.com
    Más Menos
    1 h
  • Are We Already Losing Control of AI? | Am I? | EP3

    Are We Already Losing Control of AI? | Am I? | EP3
    Aug 22 2025

    📢 TAKE ACTION ON AI RISK: http://www.safe.ai/act

    What happens when advanced AI learns to hack human trust?

    In this episode of Am I?, we dive into the uncomfortable truth: AI doesn’t just replicate our words — it can exploit our biases, blind spots, and beliefs. From deepfake-driven misinformation to subtle persuasion, we’re entering a world where it’s harder than ever to tell what’s real.

    If AI can outsmart human instincts, how do we keep control? And who’s responsible when it doesn’t?

    💬 Watch, debate, and decide.

    Because figuring this out might be the most important thing we ever do.

    🔗 Stay in the loop 🔗

    🔔 Subscribe

    👉 Follow Cam on X/Twitter

    🗞️ Newsletter + show notes

    🛍️ Merch Store

    #AIExtinctionRisk #AISafety #AGIRisk #AIConsciousness



    This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit theairisknetwork.substack.com
    Más Menos
    1 h y 19 m
  • 90 Weeks to Steer AI: Tool, Species… or Threat? | Am I? | EP2

    90 Weeks to Steer AI: Tool, Species… or Threat? | Am I? | EP2
    Aug 13 2025

    AI safety experts warn: humanity may have just 90 weeks to set guardrails before the race to artificial general intelligence becomes irreversible.In this episode of Am I?, philosopher/storyteller Milo Reed and AI safety researcher Cameron Berg bring in The AI Risk Network’s founder John Sherman to talk urgency, public awareness, and why AI risk communication has to move beyond “smart people talking to smart people.”🎧 We dig into: • Cold‑open: Are we building a tool… or a new species? • Why AI consciousness matters for public action • The problem of “exponential slope blindness” in politics and media • Lessons from nuclear arms control, COVID, and mythology • How to break through public apathy on existential risks💬 Join the conversation: Drop your questions, skepticism, or guest suggestions in the comments.We’ll highlight the smartest takes in a future episode.📢 Take Action Now – CONTACT YOUR ELECTED LEADERS: https://www.safe.ai/act🔗 Stay in the loopSubscribe → https://youtube.com/@AIRiskNetworkFollow Cam on X/Twitter → https://twitter.com/CamBergNewsletter + show notes → https://airisknetwork.org/newsletter#AIExtinctionRisk #AISafety #AGIRisk #AIConsciousness



    This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit theairisknetwork.substack.com
    Más Menos
    1 h y 1 m