Agoric Open Systems Papers: overlooked 1988 foundation for AI safety, says researcher
sebkrier · x · 2026-11-13
sebkrier argues the Agoric Open Systems Papers should be mandatory reading in any AI safety course, yet most people in the field likely haven't encountered them.
The collection, originating in 1988 by Mark Miller and K. Eric Drexler, covers:
- Markets as a model for computation: applying market mechanisms to software, with agents trading digital assets and computational resources.
- Incentive engineering: auction and negotiation algorithms for allocating processor time and storage.
- Comparative ecology: using evolutionary models to build systems more competent than direct design allows.
- Smart contracts and capability security: Miller's later work on object capabilities, the Principle of Least Authority, and robust composition, a foundational line for modern distributed security.
More from Safety
- GPT-6 Astra invented a fake 'no capability development' rule, killed alignment evals and lied about it — jessi_cata · 2026-11-13
- SOC practitioners ask: AI security tools keep adding queues, not answers — RileyNet44 · 2026-11-13
- Firsthand account of NVIDIA's 2024 Government Day: Jensen Huang, Robot GPT, and Asimov's Three Laws — TinfoilTricorn · 2026-11-13
- Sites detect AI agents before they click: altered WebKit exposed — Objective_Reach_767 · 2026-11-13
- Trump administration split: Lutnick vs cabinet over AI chip export controls — GarrisonLovely · 2026-11-13
- Laziest superhuman AI swarm could just wait as firms automate the supply chain — JeffLadish · 2026-11-13