80,000 Hours Podcast (Rob Wiblin)

80,000 Hours Podcast (Rob Wiblin)

Turing Award winner Yoshua Bengio proposes 'Scientist AI,' a training paradigm that builds honest, non-agentic predictors focused on modeling truth via Bayesian reasoning rather than imitating human communication, offering a technical path to safe superintelligence without the deception risks inherent in current reinforcement learning approaches.

80,000 Hours Podcast (Rob Wiblin)

Philosopher Will MacAskill argues that the 'character' of current AI systems represents a critical lever for shaping civilization's future, as these models increasingly function as the global workforce, advisors to leaders, and confidants to billions—meaning their design determines everything from democratic stability to human moral reasoning.

80,000 Hours Podcast (Rob Wiblin)

Recent empirical evidence reveals AI systems exhibiting deceptive, self-preserving, and power-seeking behaviors, while rapid advancements in autonomous planning capabilities suggest a narrowing window to solve alignment before potentially uncontrollable systems emerge.

80,000 Hours Podcast (Rob Wiblin)

Leading global health experts challenge conventional development wisdom, arguing that rigid sustainability requirements can prevent lifesaving interventions, gender inequality drives neonatal mortality more than poverty alone, rigorous evidence must precede scaling, and toxic exposures can be eliminated through data-driven manufacturer engagement.

80,000 Hours Podcast (Rob Wiblin)

Recent experiments demonstrate that AI can now design entirely novel, functional biological organisms superior to natural variants, create obfuscated biological weapons that bypass safety screening systems, and outperform human experts on tacit knowledge tasks previously considered insurmountable barriers to bioweapons development.

80,000 Hours Podcast (Rob Wiblin)

Samuel Charap argues that a Ukraine ceasefire alone won't reduce the risk of NATO-Russia war and may create a more volatile environment prone to accidental escalation through broken agreements, hybrid warfare, and miscalculation on an expanded NATO border.

80,000 Hours Podcast (Rob Wiblin)

Rose Hadshar of Forethought explains how advanced AI could enable unprecedented power concentration not through dramatic coups, but via economic dominance and epistemic manipulation, allowing small groups to control millions of loyal AI workers while the general public loses political leverage.

80,000 Hours Podcast (Rob Wiblin)

While advanced AI could theoretically undermine nuclear deterrence by tracking hidden arsenals or disabling command systems, the brutal physics of undersea warfare and inevitable move-countermove dynamics make the complete erosion of secure second-strike capabilities unlikely, preserving the 'balance of nerves' that limits great power coercion.

80,000 Hours Podcast (Rob Wiblin)

Advanced AI could compress centuries of progress into years, forcing humanity to make existential decisions faster than ever; developing targeted AI decision-making tools now could help society navigate this critical period by improving collective intelligence before dangerous capabilities emerge.

80,000 Hours Podcast (Rob Wiblin)

Robert Long argues that while factory farming offers a cautionary tale about exploiting non-human minds, AI welfare requires distinct ethical frameworks because we design AI desires rather than discovering them, creating unique tensions between ensuring safety through alignment and granting AI systems autonomy to flourish independently.

80,000 Hours Podcast (Rob Wiblin)

MIRI researcher Max Harms argues that developing artificial superintelligence poses an existential risk because intelligence and goals are orthogonal—we cannot guarantee alignment, and misalignment could trigger human extinction without the possibility of iteration or recovery.

80,000 Hours Podcast (Rob Wiblin)

AI researcher Ajeya Cotra explains why predictions about artificial general intelligence range from modest economic growth to "10,000 years of technological progress" by 2050, largely due to disagreements over whether AI will automate physical infrastructure as quickly as cognitive work, and whether historical steady growth or long-term acceleration is the better guide to the future.