ControlAI’s Connor Leahy on why superintelligence is ‘not a weapon, it’s an adversary’
ControlAI's Connor Leahy argues superintelligence is an unmanageable adversary, backs the Sanders-Casar 'Ban Superintelligence Act' and international verification agreements.
On TechCrunch's Equity podcast, ControlAI's US Executive Director Connor Leahy argued that alignment and containment alone cannot manage superintelligence risk and advocated halting frontier development, citing the Sanders-Casar 'Ban Superintelligence Act' and parallel UK legislation ControlAI advised on. He characterized frontier AI labs as political actors, pointed to the OpenAI-related Hugging Face breach as evidence of danger, and called AI self-improvement the point of no return, endorsing international 'trust but verify' agreements.
- Leahy advocates stopping superintelligence development rather than relying on alignment
- Cites Sanders-Casar US bill and UK legislation ControlAI advised on
- Claims AI self-improvement marks the point of no return
- Calls for international 'trust but verify' agreements including with China
- Vendors
- TechCrunchOpenAIHugging Face
- Organizations
- ControlAIEquity Podcast
From the original article
2 min read at techcrunch.com
AI companies have been talking about superintelligent AI like it’s inevitable, but recent safety incidents like OpenAI’s Hugging Face breach are demonstrating the potential dangers of deploying AI systems that are more capable than humans. So what happens when we can’t reliably control what these systems do?
By Rebecca Bellan, Theresa Loconsolo · techcrunch.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.