MIGHT THE ROBOTS TAKE OVER? [Prof. Yoshua Bengio]
About
No channel description available.
Video Description
Professor Yoshua Bengio is a pioneer in deep learning and Turing Award winner. Bengio talks about AI safety, why goal-seeking “agentic” AIs might be dangerous, and his vision for building powerful AI tools without giving them agency. Topics include reward tampering risks, instrumental convergence, global AI governance, and how non-agent AIs could revolutionize science and medicine while reducing existential threats. Perfect for anyone curious about advanced AI risks and how to manage them responsibly. SPONSOR MESSAGES: *** CentML offers competitive pricing for GenAI model deployment, with flexible options to suit a wide range of models, from small to large-scale deployments. https://centml.ai/pricing/ Tufa AI Labs is a brand new research lab in Zurich started by Benjamin Crouzier focussed on o-series style reasoning and AGI. Are you interested in working on reasoning, or getting involved in their events? Goto https://tufalabs.ai/ *** Interviewer: Tim Scarfe Yoshua Bengio: https://x.com/Yoshua_Bengio https://scholar.google.com/citations?user=kukA0LcAAAAJ&hl=en https://yoshuabengio.org/ https://en.wikipedia.org/wiki/Yoshua_Bengio TOC: 1. AI Safety Fundamentals [00:00:00] 1.1 AI Safety Risks and International Cooperation [00:03:20] 1.2 Fundamental Principles vs Scaling in AI Development [00:11:25] 1.3 System 1/2 Thinking and AI Reasoning Capabilities [00:15:15] 1.4 Reward Tampering and AI Agency Risks [00:25:17] 1.5 Alignment Challenges and Instrumental Convergence 2. AI Architecture and Safety Design [00:33:10] 2.1 Instrumental Goals and AI Safety Fundamentals [00:35:02] 2.2 Separating Intelligence from Goals in AI Systems [00:40:40] 2.3 Non-Agent AI as Scientific Tools [00:44:25] 2.4 Oracle AI Systems and Mathematical Safety Frameworks 3. Global Governance and Security [00:49:50] 3.1 International AI Competition and Hardware Governance [00:51:58] 3.2 Military and Security Implications of AI Development [00:56:07] 3.3 Personal Evolution of AI Safety Perspectives [01:00:25] 3.4 AI Development Scaling and Global Governance Challenges [01:12:10] 3.5 AI Regulation and Corporate Oversight 4. Technical Innovations [01:23:00] 4.1 Evolution of Neural Architectures: From RNNs to Transformers [01:26:02] 4.2 GFlowNets and Symbolic Computation [01:30:47] 4.3 Neural Dynamics and Consciousness [01:34:38] 4.4 AI Creativity and Scientific Discovery SHOWNOTES (Transcript, references, best clips etc): https://www.dropbox.com/scl/fi/ajucigli8n90fbxv9h94x/BENGIO_SHOW.pdf?rlkey=38hi2m19sylnr8orb76b85wkw&dl=0 CORE REFS (full list in shownotes and pinned comment): [00:00:15] Bengio et al.: "AI Risk" Statement https://www.safe.ai/work/statement-on-ai-risk [00:23:10] Bengio on reward tampering & AI safety (Harvard Data Science Review) https://hdsr.mitpress.mit.edu/pub/w974bwb0 [00:40:45] Munk Debate on AI existential risk, featuring Bengio https://munkdebates.com/debates/artificial-intelligence [00:44:30] "Can a Bayesian Oracle Prevent Harm from an Agent?" (Bengio et al.) on oracle-to-agent safety https://arxiv.org/abs/2408.05284 [00:51:20] Bengio (2024) memo on hardware-based AI governance verification https://yoshuabengio.org/wp-content/uploads/2024/08/FlexHEG-Memo_August-2024.pdf [00:56:15] 2018 Turing Award to Bengio, Hinton, LeCun for deep learning https://awards.acm.org/about/2018-turing [01:12:55] Bengio’s involvement in EU AI Act code of practice https://digital-strategy.ec.europa.eu/en/news/meet-chairs-leading-development-first-general-purpose-ai-code-practice [01:27:05] Complexity-based compositionality theory (Elmoznino, Jiralerspong, Bengio, Lajoie) https://arxiv.org/abs/2410.14817 [01:29:00] GFlowNet Foundations (Bengio et al.) for probabilistic inference https://arxiv.org/pdf/2111.09266 [01:32:10] Discrete attractor states in neural systems (Nam, Elmoznino, Bengio, Lajoie) https://arxiv.org/pdf/2302.06403
Craft Valentine's Magic
AI-recommended products based on this video

Collapsible Car Trash Bin, 23.5 cm Portable Waste Container with Lid, Black and Red

Interactive Cat Toy for Indoor Cats Fast Rolling on Carpet, Speedy Tail 2.0 Cat Toy, Three Working Modes 360° Smart Automatic Rolling Cat Ball Toys for Bored Indoor Cats and Dogs - Red

Ipetboom Baby Graduation Cap Toddler Grad Hat Photo Props for Newborn Photography and Preschool Cosplay with Red Tassel

Handmade 2-Piece Baby Canada Set, Custom Handmade Canada Maple Leaf Long Sleeve Footed Zippered Baby Bodysuit and Hat Set (Bright Red, 3-6 months)

Personalized 2026 Graduation Gifts, Custom Graduation Mug With Initial Name, High School College Masters Degree Phd Graduations Gift,11 oz Graduations Cup, Class of 2026 Gifts, Monogram Coffee Mug

Graduation Gifts for Her Him, Custom Graduation Mug with Name, Class of 2026 Gifts Mastered It Coffee Mug, High School College Masters Degree Phd Graduate Gift, Personalized Grad Gift Coffee Cup

Graduation Gifts for Her Him, Custom Graduation Mug with Name, Class of 2026 Gifts, High School College Masters Degree Phd Graduations Gift, Personalized Grad Coffee Cup Graduate Gift

FAURAPMNG FAURAPMNG 5 Pcs Graduation Cap Photo Charm Graduate Memorial Tassel Picture Charms with Angel Wing Personalized Bouquet Tassel DIY Grad Photo Chain for Class of Grad Cap Gown Ceremony Caps Charm Decor

HONYUEYIM 2 PCS Magnetic Couples Bracelets for Women Men,Natural Stone Stone Beads Bracelet His and Hers Relationship Bracelet for Boyfriend Girlfriend Valentines Day Gifts (Purple + Black)

Volunboy Boys Clothes Set Toddler Kids Gentlemen Suit Long Sleeve Bow Tie Shirts Suspenders Pants Outfits

Collapsible Car Trash Bin, 23.5 cm Portable Waste Container with Lid, Black and Red

Interactive Cat Toy for Indoor Cats Fast Rolling on Carpet, Speedy Tail 2.0 Cat Toy, Three Working Modes 360° Smart Automatic Rolling Cat Ball Toys for Bored Indoor Cats and Dogs - Red

Ipetboom Baby Graduation Cap Toddler Grad Hat Photo Props for Newborn Photography and Preschool Cosplay with Red Tassel

![Abstraction & Idealization: AI's Plato Problem [Mazviita Chirimuuta]](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/yq318DIwPqw/hqdefault.jpg)
![Why Every Brain Metaphor in History Has Been Wrong [SPECIAL EDITION]](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/pO0WZsN8Oiw/hqdefault.jpg)
![AutoGrad Changed Everything (Not Transformers) [Dr. Jeff Beck]](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/9suqiofCiwM/hqdefault.jpg)
![Why Scientists Can't Rebuild a Polaroid Camera [César Hidalgo]](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/vzpFOJRteeI/hqdefault.jpg)

![Why High Benchmark Scores Don’t Mean Better AI [SPONSORED]](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/rqiC9a2z8Io/hqdefault.jpg)
![The Mathematical Foundations of Intelligence [Professor Yi Ma]](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/QWidx8cYVRs/hqdefault.jpg)

![Tensor Logic "Unifies" AI Paradigms [Pedro Domingos]](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/4APMGvicmxY/hqdefault.jpg)

![He Co-Invented the Transformer. Now: Continuous Thought Machines [Llion Jones / Luke Darlow]](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/DtePicx_kFY/hqdefault.jpg)


![We Built Calculators Because We're STUPID! [Prof. David Krakauer]](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/dY46YsGWMIc/hqdefault.jpg)
![Why Humans Are Still Powering AI [Sponsored] - Phelim Bradley](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/R11ESdfVX64/hqdefault.jpg)
![The Universal Hierarchy of Life - Prof. Chris Kempes [SFI]](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/iwClZ-7OweY/hqdefault.jpg)

![Google Researcher Shows Life "Emerges From Code" [Blaise Agüera y Arcas]](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/rMSEqJ_4EBk/hqdefault.jpg)
![AI training data will never be fully synthetic [SPONSORED]](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/cnxZZTl1tkk/hqdefault.jpg)
![AI Agents can write 10,000 lines of hacking code in seconds [Dr. Ilia Shumailov]](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/aoX_pGQMbEM/hqdefault.jpg)