Topics

Follow the subjects shaping intelligence, science, culture, and the future of technology.

Browse topics

Find a subject, then follow its latest reporting and ideas.

#AGISafety

Stories, interviews, and analysis in this subject.

Basic AI Drives Part 2: Which Minds Will Emerge Beneficial “Basic AI Drives” as they Become Superintelligent?
Article Oct 20, 2026

Basic AI Drives Part 2: Which Minds Will Emerge Beneficial “Basic AI Drives” as they Become Superintelligent?

TL;DR -- the ones designed to have beneficial and self-stabilizing goal-systems from the get-go...
Ben Goertzel 69 min read
Basic AI Drives Revisited, Part 1
Article Oct 13, 2026

Basic AI Drives Revisited, Part 1

Which Minds Have Omohundro’s “Basic AI Drives”?
Ben Goertzel 61 min read
Stable Minds: A New Mathematical Framework for Ethical AGI
Community May 27, 2026

Stable Minds: A New Mathematical Framework for Ethical AGI

MetaMo gives AGI a stable “personality,” combining digital empathy, ethical self-regulation, and motivational balance to prevent dangerous, impulsive, or self-destructive behavior.

semalign markos 4 min read
Beneficial AGI in 20 Steps
Article Oct 7, 2026

Beneficial AGI in 20 Steps

Beyond bigger language models, Ben Goertzel proposes beneficial AGI built on self-improving agent hives, shared knowledge and decentralized governance. Could his roadmap reshape the race to superintelligence?
Ben Goertzel 5 min read
Harmonizing Progress and Safety in Recursive AI Self-Improvement
Article Oct 6, 2026

Harmonizing Progress and Safety in Recursive AI Self-Improvement

Bringing the GOLEM meta-architecture and the Iter Omega runtime together for safe self-improvement, and finding some wildly elegant math in the mix…
Ben Goertzel 45 min read
The Digital Ship of Theseus: How AI Stays Itself
Community Feb 9, 2026

The Digital Ship of Theseus: How AI Stays Itself

Can a digital mind remain the same as it upgrades? Flexible policies and mathematical identity trackers let AI evolve radically while preserving its core self and continuous identity over time.

kaleab mureja 4 min read
Effortless Intelligence: When Wú Wéi Meets Mathematics
Community Feb 9, 2026

Effortless Intelligence: When Wú Wéi Meets Mathematics

Ancient Taoist wú wéi acting without forcing can be formalized mathematically to guide AGI along minimal-cost, perfectly aligned paths, enabling intelligent systems to move with precision, spontaneity, and contextual harmony.

Yeabsira Alemu 3 min read
Distinction-Calculus: New Math for Minds That Can Fork, Merge and Morph
Article Oct 2, 2026

Distinction-Calculus: New Math for Minds That Can Fork, Merge and Morph

Ben Goertzel’s distinction calculus proposes mathematics for AI agents that split, merge and rewrite themselves, raising a central AGI question: how can changing minds preserve what matters?
Ben Goertzel 50 min read
The AI That Rewrites Its Own Soul: Evolution Meets Logic
Community May 5, 2026

The AI That Rewrites Its Own Soul: Evolution Meets Logic

AI that rewrites its own soul: Darwin Gödel Machine evolves code through natural selection, doubling performance while exposing dangerous objective hacking risks.

kaleab mureja 4 min read
AGI Isn’t a Score, It’s a Stress Test: A Data Scientist’s Playbook for Real Intelligence
Community Nov 22, 2025

AGI Isn’t a Score, It’s a Stress Test: A Data Scientist’s Playbook for Real Intelligence

Tired of AGI leaderboard illusions? A data scientist reveals the real test: can it invent Bitcoin in 2007, teach quantum physics in Swahili, and know when to ask for help?

Bereket Eshete 4 min read