Podcast
Joe Carlsmith Audio
Hosted by Joe Carlsmith · EN
Audio versions of essays by Joe Carlsmith. Philosophy, futurism, and other topics. Text versions at joecarlsmith.com.
16episodes
Episodes
Newest firstAll episodes
On restraining AI development for the sake of safety
Mar 1901:22:21Tap to summarizeMy take on slowing down AI. Text version here: https://joecarlsmith.com/2026/03/19/on-restraining-ai-development-for-the-sake-of-safety/
Transcribe →
Building AIs that do human-like philosophy
Jan 2900:33:33Tap to summarizeAIs 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/
Transcribe →
How human-like do safe AI motivations need to be?
Nov 1201:23:32Tap to summarizeAIs with alien motivations can still follow instructions safely on the inputs that matter. Text version here: https://joecarlsmith.com/2025/11/12/how-human-like-do-safe-ai-motivations-need-to-be/
Transcribe →
Leaving Open Philanthropy, going to Anthropic
Nov 300:32:09Tap to summarizeOn 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/
Transcribe →
Controlling the options AIs can pursue
Sep 2900:55:34Tap to summarizeOn boxing AIs, and on making deals with them. Text version here: https://joecarlsmith.com/2025/09/29/controlling-the-options-ais-can-pursue
Transcribe →
Giving AIs safe motivations
Aug 1801:23:25Tap to summarizeA four-step picture. Text version here: https://joecarlsmith.com/2025/08/18/giving-ais-safe-motivations
Transcribe →
The stakes of AI moral status
May 21, 202500:37:29Tap to summarizeOn seeing and not seeing souls. Text version here: https://joecarlsmith.com/2025/05/21/the-stakes-of-ai-moral-status/
Transcribe →
Can we safely automate alignment research?
Apr 30, 202501:29:38Tap to summarizeIt'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/. There's also a video and transcript of a talk I gave on this topic here: https://joecarlsmith.com/2025/04/30/video-and-transcript-of-talk-on-automating-alignment-research/
Transcribe →
AI for AI safety
Mar 14, 202500:27:51Tap to summarizeWe 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
Transcribe →
Paths and waystations in AI safety
Mar 11, 202500:18:07Tap to summarizeOn the structure of the path to safe superintelligence, and some possible milestones along the way. Text version here: https://joecarlsmith.substack.com/p/paths-and-waystations-in-ai-safety
Transcribe →