The Inside View
Ein Podcast von Michaël Trazzi
54 Folgen
-
Owain Evans - AI Situational Awareness, Out-of-Context Reasoning
Vom: 23.8.2024 -
[Crosspost] Adam Gleave on Vulnerabilities in GPT-4 APIs (+ extra Nathan Labenz interview)
Vom: 17.5.2024 -
Ethan Perez on Selecting Alignment Research Projects (ft. Mikita Balesni & Henry Sleight)
Vom: 9.4.2024 -
Emil Wallner on Sora, Generative AI Startups and AI optimism
Vom: 20.2.2024 -
Evan Hubinger on Sleeper Agents, Deception and Responsible Scaling Policies
Vom: 12.2.2024 -
[Jan 2023] Jeffrey Ladish on AI Augmented Cyberwarfare and compute monitoring
Vom: 27.1.2024 -
Holly Elmore on pausing AI
Vom: 22.1.2024 -
Podcast Retrospective and Next Steps
Vom: 9.1.2024 -
Kellin Pelrine on beating the strongest go AI
Vom: 4.10.2023 -
Paul Christiano's views on "doom" (ft. Robert Miles)
Vom: 29.9.2023 -
Neel Nanda on mechanistic interpretability, superposition and grokking
Vom: 21.9.2023 -
Joscha Bach on how to stop worrying and love AI
Vom: 8.9.2023 -
Erik Jones on Automatically Auditing Large Language Models
Vom: 11.8.2023 -
Dylan Patel on the GPU Shortage, Nvidia and the Deep Learning Supply Chain
Vom: 9.8.2023 -
Tony Wang on Beating Superhuman Go AIs with Advesarial Policies
Vom: 4.8.2023 -
David Bau on Editing Facts in GPT, AI Safety and Interpretability
Vom: 1.8.2023 -
Alexander Pan on the MACHIAVELLI benchmark
Vom: 26.7.2023 -
Vincent Weisser on Funding AI Alignment Research
Vom: 24.7.2023 -
[JUNE 2022] Aran Komatsuzaki on Scaling, GPT-J and Alignment
Vom: 19.7.2023 -
Nina Rimsky on AI Deception and Mesa-optimisation
Vom: 18.7.2023
The goal of this podcast is to create a place where people discuss their inside views about existential risk from AI.