Joe Carlsmith Audio
de Joe Carlsmith
Cel mai nou episod
On restraining AI development for the sake of safety
On restraining AI development for the sake of safety
Despre acest podcast
Audio versions of essays by Joe Carlsmith. Philosophy, futurism, and other topics. Text versions at joecarlsmith.com.
Episoade
Cele mai noi 20 din 71 episoade
- On restraining AI development for the sake of safety · 1 h 22 minMy take on slowing down AI. Text version here: https://joecarlsmith.com/2026/03/19/on-restraining-ai-development-for-the-sake-of-safety/
- Building AIs that do human-like philosophy · 34 minAIs will face philosophical questions humans can't answer for them. Text version here: https://joecarlsmith.com/2026/01/29/building-ais-that-do-human-like-philosophy/
- How human-like do safe AI motivations need to be? · 1 h 23 minAIs with alien motivations can still follow instructions safely on the inputs that matter. Text version here…
- Leaving Open Philanthropy, going to Anthropic · 32 minOn a career move, and on AI-safety-focused people working at AI companies. Text version here: https://joecarlsmith.com/2025/11/03/leaving-open-philanthropy-going-to-anthropic/
- Controlling the options AIs can pursue · 56 minOn boxing AIs, and on making deals with them. Text version here: https://joecarlsmith.com/2025/09/29/controlling-the-options-ais-can-pursue
- Giving AIs safe motivations · 1 h 23 minA four-step picture. Text version here: https://joecarlsmith.com/2025/08/18/giving-ais-safe-motivations
- The stakes of AI moral status · 37 minOn seeing and not seeing souls. Text version here: https://joecarlsmith.com/2025/05/21/the-stakes-of-ai-moral-status/
- Can we safely automate alignment research? · 1 h 29 minIt's really important; we've got a real shot; there are a ton of ways to fail. Text version here: https://joecarlsmith.com/2025/04/30/can-we-safely-automate-alignment-research/…
- AI for AI safety · 28 minWe should try extremely hard to use AI labor to help address the alignment problem. Text version here: https://joecarlsmith.com/2025/03/14/ai-for-ai-safety
- Paths and waystations in AI safety · 18 minOn the structure of the path to safe superintelligence, and some possible milestones along the way. Text version here…
- When should we worry about AI power-seeking? · 47 minExamining the conditions required for rogue AI behavior. Text version here: https://joecarlsmith.substack.com/p/when-should-we-worry-about-ai-power
- What is it to solve the alignment problem? · 40 minAlso: to avoid it? Handle it? Solve it forever? Solve it completely? Text version here: https://joecarlsmith.substack.com/p/what-is-it-to-solve-the-alignment
- How do we solve the alignment problem? · 9 minIntroduction to a series of essays about paths to safe and useful superintelligence. Text version here: https://joecarlsmith.substack.com/p/how-do-we-solve-the-alignment-problem
- Fake thinking and real thinking · 1 h 18 minWhen the line pulls at your hand. Text version here: https://joecarlsmith.com/2025/01/28/fake-thinking-and-real-thinking/.
- Takes on "Alignment Faking in Large Language Models" · 1 h 27 minWhat can we learn from recent empirical demonstrations of scheming in frontier models? Text version here: https://joecarlsmith.com/2024/12/18/takes-on-alignment-faking-in-large-la…
- (Part 2, AI takeover) Extended audio from my conversation with Dwarkesh Patel · 2 h 7 minExtended audio from my conversation with Dwarkesh Patel. This part focuses on the basic story about AI takeover. Transcript available on my website here…
- (Part 1, Otherness) Extended audio from my conversation with Dwarkesh Patel · 3 h 58 minExtended audio from my conversation with Dwarkesh Patel. This part focuses on my series "Otherness and control in the age of AGI." Transcript available on my website here…
- Introduction and summary for "Otherness and control in the age of AGI" · 12 minThis is the introduction and summary for my series "Otherness and control in the age of AGI." Text version here…
- Second half of full audio for "Otherness and control in the age of AGI" · 4 h 11 minSecond half of the full audio for my series on how agents with different values should relate to one another, and on the ethics of seeking and sharing power. First half here…
- First half of full audio for "Otherness and control in the age of AGI" · 3 h 7 minFirst half of the full audio for my series on how agents with different values should relate to one another, and on the ethics of seeking and sharing power. Second half here…
