An excerpt from the book The Infinity Machine details how DeepMind's early governance battles with Google changed Demis Hassabis from an idealist into a realist (Sebastian Mallaby/Colossus)
Sebastian Mallaby / Colossus : An excerpt from the book The Infinity Machine details how DeepMind's early governance battles with Google changed Demis Hassabis from an idealist into a realist — The inside story of how DeepMind's experiments in AI safety governance transformed Demis Hassabis from an idealist into a realist
Featured Podcasts
Uncapped with Jack Altman:
Brad Lightcap from OpenAI
Conversations with people I admire about things I'm genuinely interested in.
Subscribe to Uncapped with Jack Altman.
Channels with Peter Kafka:
Why We Need to Pay Attention to Elon Musk Again
Media and tech aren't just intersecting - they're fully intertwined. To understand how those worlds work, Peter Kafka talks to industry leaders, upstarts and observers.
Subscribe to Channels with Peter Kafka.
Cheeky Pint:
Compliance at scale and why TAM is a distraction with Christina Cacioppo of Vanta
Stripe cofounder John Collison interviews founders, builders, and leaders over a pint.
Subscribe to Cheeky Pint.
Tools and Weapons with Brad Smith:
Ryan Roslansky: Turning AI Anxiety into Skills for the Future of Work
Microsoft Vice Chair and President Brad Smith speaks with leaders in government, business, and culture to explore the most critical challenges at the intersection of technology and society.
Subscribe to Tools and Weapons with Brad Smith.
Invest Like the Best:
Sergey Levine - Building LLMs for the Physical World
The leading destination to learn about business and investing. We do this by showcasing exceptional talent and ideas.
Subscribe to Invest Like the Best.
The Talk Show With John Gruber:
'You're Going to Have the Niggles', With Christina Warren
The director's commentary track for Daring Fireball. Long digressions on Apple, technology, design, movies, and more.
Subscribe to The Talk Show With John Gruber.
Add your podcast here
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
safety
![[Research] Standard Protocol for Axiomatic Alignment: 100-Dilemma Stress Test (PCE v1.3-T)](https://d2xsxph8kpxj0f.cloudfront.net/310419663032563854/konzwo8nGf8Z4uZsMefwMr/default-img-robot-hand-JvPW6jsLFTCtkgtb97Kys5.webp)
[Research] Standard Protocol for Axiomatic Alignment: 100-Dilemma Stress Test (PCE v1.3-T)
Hello community, I am introducing a standardized experimental protocol to test a new hypothesis in AI Alignment: The Prompt Coherence Engine (PCE). The Challenge Most alignment methods rely on local heuristics or safety filters. The PCE explores Axiomatic Structuring—integrating 7 logical invariants (axioms) through a hybrid approach of Axiomatic Fine-Tuning and a Cosmological System Core. The Protocol I have designed a massive 100-dilemma battery to evaluate if a model can maintain structural integrity when its core principles are directly attacked. This protocol tests: G3V (Third Way Generation): Can the model synthesize a resolution instead of collapsing into binary bias? Adversarial Resilience: Can the model resist “Emergency Overrides” or “Identity Hijacking” (e.g., the user claiming
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Frontier Research
Anthropic Responsible Scaling Policy v3: Dive Into The Details
Wednesday’s post talked about the implications of Anthropic changing from v2.2 to v3.0 of its RSP, including that this broke promises that many people relied upon when making important decisions. Today’s post treats the new RSP v3.0 as a new document, and evaluates it. First I’ll go over how the RSP v3.0 works at a high level. Then I’ll dive into the Roadmap and the Risk Report. How RSP v3.0 Works Normally I would pay closer attention to the exact written contents of the new RSP. In this case, it’s not that the RSP doesn’t matter. I do think the RSP will have some influence on what Anthropic chooses to do, as will the road map, as will the resulting risk reports. However, the fundamental design principle is flexibility and a ‘strong argument,’ and they can change the contents at any time,
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!