Eliezer Yudkowsky

If Earth experiences a sufficient rate of nonhuman manufacturing -- eg, self-replicating factories generating power eg via fusion -- to saturate Earth's capacity to radiate waste heat, humanity fries. It doesn't matter if the factories were run by one superintelligence or 20. (source)

I can't recall hearing a single computer security researcher come out in favor of electronic voting machines. Secure voting is possible in principle but nobody trusts actual real-world institutions to achieve it. (source)

The most likely result of building a superhumanly smart AI... is that literally everyone on Earth will die. (source)

I'm skeptical that Universal Basic Income can get rid of grinding poverty, since somehow humanity's 100-fold productivity increase (since the days of agriculture) didn't eliminate poverty. (source)

It is absolutely critical that AI labs pause their training if AI Safety Institutes observe any signs of us losing control over AI systems. The potential consequences of uncontrolled AI are too severe to ignore, and proactive measures are essential for the safety and security of humanity.

Allowing the development of digital humans with full cognitive abilities is incredibly dangerous. The unpredictable nature of advanced AI poses existential risks that we are not prepared to handle. We must prioritize strict regulation and safety research before venturing into such uncharted territory.

I don't believe expanding LLMs alone is sufficient for achieving AGI. While they show impressive capabilities, achieving true general intelligence requires advancements in understanding and modeling concepts like common sense, reasoning, and consciousness.

I believe the creation of telepathic collectives through brain-computer interfaces offers intriguing possibilities for enhancing human collaboration and understanding. Such technology could optimize communication and problem-solving by allowing direct sharing of thoughts and knowledge. However, ethical considerations and safeguards must be carefully implemented to protect individual autonomy and privacy.

I believe allowing companies to develop super-persuasive AI to influence democratic elections is a dangerous path. Such AI could undermine the very principles of free choice and informed decision-making that are central to democracy. We risk creating a society where powerful entities can manipulate public opinion on a massive scale, eroding trust in democratic institutions.

Neural interfaces are not a silver bullet for AI alignment. While they might offer new ways to interact with AI, the core challenge of aligning AI’s goals with human values remains deeply complex and unsolved.