AI Reasoning · IEEE Spectrum AI
All may not be shed, the scientists say
Compiled by KHAO Editorial — aggregated from 10 outlets. See llms.txt for citation guidance.
◌ Single Source
The May issue of IEEE Spectrum is here!
Key facts
- IEEE Spectrum: Would you say your work is fundamentally against AI
- IEEE Spectrum: You and your colleagues have now shown that misalignment of AI systems is inevitable, because any AI system complex enough to display general intelligence will produce unpredictable
- The team spoke with Hector Zenil, associate professor of healthcare and biomedical Engineering at King’s College London, about his and his colleagues’ work on alignment’s limits and its future
- To cope with this impossibility, they suggest a strategy involving pitting AI systems with different modes of reasoning and partially overlapping goals against each other
Summary
Maybe the best they can do is make “neurodiverse” systems that challenge each other. One of the hardest problems in artificial intelligence is “ alignment,” or making sure AI goals match their own, a challenge that may prove especially important if superintelligent AIs that outmatch them intellectually are ever developed. All may not be lost, the scientists say. The team spoke with Hector Zenil, associate professor of healthcare and biomedical Engineering at King’s College London, about his and his colleagues’ work on alignment’s limits and its future. The simplest way to put it is this: Do not trust one supposedly perfect AI to govern everything.