Coasean economics of agent swarms - by Herbie Bradley
pathwaysai.org · 2,724 words · saved by 1 readers
What is continual learning, really?
Despite the immense capabilities of current AI agents, they struggle to absorb new knowledge from their interactions with users, learn user preferences over time, or internalize insights from rare events across their work. It’s now common to talk about how continual learning is a huge missing capability in AI, which if solved could unlock a significantly different shape of intelligence, and further leaps forward. Currently, continual learning is entirely explicit: in the form of increasingly complex harnesses and scaffolds. Massive databases of text files are assembled and injected into the…
saved by
related reading
- Coasean economics of agent swarmspathwaysai.org
- Why We Need Continual Learning | Andreessen Horowitza16z.com
- AI 2027ai-2027.com
- Supermemory — Memory and continual learning for agentssupermemory.ai
- Why Tool AIs Want to Be Agent AIs · Gwern.netgwern.net
- Continual Learning in Token Space | Lettaletta.com
- Agent swarms and the new model economics · Cursorcursor.com
- Memory Models: Towards Agents That Learnletta.com
- Questions about the Future of AI - by Dwarkesh Pateldwarkesh.com
- Your Left Brain Doesn't Trade With Your Right — LessWronglesswrong.com
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- Announcing our investment in Engram, the memory dream team — Amplify Partnersamplifypartners.com