Publishing Details
About This Podcast
A RSS feed with papers which are von interest in AI Safety Control and Agent Behavior
Podcasting 2.0 Features
Explore Statistics
Recent Episodes
Anthrophic Mythos
Anthrophic Mythos
Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
S1E14 Public Finance in the Age of AI
Public Finance in the Age of AI
S1E13 Neural Steering Vectors Reveal Dose and Exposure-Dependent Impacts of Human-AI Relationships
Neural Steering Vectors Reveal Dose and Exposure-Dependent Impacts of Human-AI Relationships
S1E12 The Generative AI Paradox
The Generative AI Paradox
S1E11 Training Agents to Self-Report Misbehavior
Training Agents to Self-Report Misbehavior
S1E10 Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models
Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models
S1E9 The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systems
The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systems
S1E8 The Generative AI Paradox: How Synthetic Realities Erode Shared Epistemic Ground
The Generative AI Paradox: How Synthetic Realities Erode Shared Epistemic Ground
S1E7 Evaluating Frontier Models for Stealth and Situational Awareness
Evaluating Frontier Models for Stealth and Situational Awareness
S1E6 Evaluating Frontier Models for Stealth and Situational Awareness
Evaluating Frontier Models for Stealth and Situational Awareness
S1E5 RASP Discovering Interpretable Algorithms by Decompiling Transformers into Human-Readable Programs
Discovering Interpretable Algorithms by Decompiling Transformers into Human-Readable Programs
S1E4 Reducing Harmful Generative AI Outputs via Consensus Sampling
Reducing Harmful Generative AI Outputs via Consensus Sampling
AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
S1E2 Bridging Skill Gaps for the Future: New Jobs Creation in the AI Age
The demand and supply of new skills—especially in IT and AI—are reshaping labor markets,impacting wages and hiring. About 1 in 10 job vacancies in advanced economies demands at least one newskill,…
S1E1 Reasoning Models Struggle to Control their Chains of Thought
Chain-of-thought (CoT) monitoring is a promising tool for detecting misbehaviorsand understanding the motivations of modern reasoning models. However, ifmodels can control what they verbalize in…
Frequently Asked Questions
AI Based Paper Discussions has published 16 episodes since March 2026, covering topics in Technology.
AI Based Paper Discussions is currently highly active with new episodes hourly. Average episode length is 20m.
