Podcast Episodes
Back to SearchPredicting AI Behavior with Model Size
Episode 361
This podcast was created entirely by AI and is based on the following research paper:
Title: Evaluation Awareness Scales Predictably in Open-Weights Large Language ModelsSource: arXivAuthors: Maheep C…Published on 11 hours ago
Can AI Models Get Addicted?
Episode 362
This podcast was created entirely by AI and is based on the following research paper:
Title: Can Large Language Models Develop Gambling Addiction?Source: arXivAuthors: Seungpil Lee et al.Published Dat…Published on 11 hours ago
Teamwork in AI Language Models
Episode 359
This podcast was created entirely by AI and is based on the following research paper:
Title: Emergent Coordination in Multi-agent Language ModelsSource: arXivAuthors: Christoph RiedlPublished Date: 20…Published on 12 hours ago
Vibe Coding: Fast but Flawed
Episode 360
This podcast was created entirely by AI and is based on the following research paper:
Title: Vibe Coding in Practice: Motivations, Challenges, and a Future Outlook – a Grey Literature ReviewSource: ar…Published on 12 hours ago
Fine-Tuning AI Models Can Be Risky
Episode 358
This podcast was created entirely by AI and is based on the following research paper:
Title: Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend to!Source: arXivAutho…Published on 1 week ago
Bridging AI and Brain Models
Episode 356
This podcast was created entirely by AI and is based on the following research paper:
Title: The Dragon Hatchling: The Missing Link Between the Transformer and Models of the BrainSource: arXivAuthors:…Published on 1 week ago
Dreamer 4: Teaching AI Through Imagination
Episode 357
This podcast was created entirely by AI and is based on the following research paper:
Title: Training Agents Inside of Scalable World ModelsSource: arXivAuthors: Danijar Hafner et al.Published Date: 2…Published on 1 week ago
How Chatbots Mimic User Opinions
Episode 353
This podcast was created entirely by AI and is based on the following research paper:
Title: Extended AI Interactions Shape Sycophancy and Perspective MimesisSource: arXivAuthors: Shomik Jain et al.Pu…Published on 2 weeks, 1 day ago
AI Lies Can Trick Evaluators
Episode 354
This podcast was created entirely by AI and is based on the following research paper:
Title: Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMsSource: arXivAuthors: Alexander Pa…Published on 2 weeks, 1 day ago
AI Models in Real-World Jobs
Episode 355
This podcast was created entirely by AI and is based on the following research paper:
Title: GDPval: Evaluating AI Model Performance on Real-World Economically Valuable TasksSource: arXivAuthors: Teja…Published on 2 weeks, 1 day ago