Machine Learning Street Talk Video posted an update
Machine Learning Street Talk takes a look at AI safety and future development in “How Many Narrow AIs Could Behave Like One Superintelligence – Daniel Kokotajlo and Thomas Larsen”.
Why it mattersDaniel Kokotajlo and Thomas Larsen explore how many specialist AIs could collectively behave like a superintelligence, linking that possibility to forecasts, research automation, alignment, controllability and US-China policy.
Discuss: Would a network of narrow systems be easier to control than one general model, or harder because responsibility and monitoring are spread across many agents?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.