Best AI papers explained

528 Episodes

1. SycEval: Benchmarking LLM Sycophancy in Mathematics and Medicine

   Published: 23/04/2025
2. Stack AI: Democratizing Enterprise AI Development

   Published: 22/04/2025
3. Evaluating Modern Recommender Systems: Challenges and Future Directions

   Published: 22/04/2025
4. AI in the Enterprise: Seven Lessons from Frontier Companies by OpenAI

   Published: 22/04/2025
5. Discussion: Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

   Published: 21/04/2025
6. AI Agent Protocols and Human Preference

   Published: 21/04/2025
7. Cross-Environment Cooperation for Zero-Shot Multi-Agent Coordination

   Published: 20/04/2025
8. Sutton and Silver: The Era of Experience: Learning Beyond Human Data

   Published: 19/04/2025
9. Sample, Don't Search: Rethinking Test-Time Alignment for Language Models

   Published: 19/04/2025
10. AI Agents: Echoes of Past Technology Pivots?

    Published: 19/04/2025
11. Minimalist LLM Reasoning: Rejection Sampling to Reinforcement

    Published: 19/04/2025
12. Securing the Model Context Protocol in Enterprise Environments

    Published: 19/04/2025
13. Improving Multi-Turn Tool Use with Reinforcement Learning

    Published: 19/04/2025
14. Cultural Knowledge Conservation and Control in Large Language Models

    Published: 19/04/2025
15. Data Quality, Repetition, and Scaling of Language Models

    Published: 18/04/2025
16. Compute-Optimal Scaling Laws for Language Models Revisited

    Published: 18/04/2025
17. Concise Reasoning via Reinforcement Learning

    Published: 18/04/2025
18. Throughput Limits for LLM Inference and AI Agent Scheduling

    Published: 14/04/2025
19. RL Post-training Amplifies Pretraining Behaviors in Language Models

    Published: 14/04/2025
20. Fast Adaptation of Behavioral Foundation Models

    Published: 14/04/2025