AI Paper Drop
Divakar Prabhu
A conversational technical podcast about recent AI and CS. Every episode, an AI system scans the latest papers on ArXiv, selects one standout piece of research, and turns it into a concise podcast episode - from paper curation and analysis to scriptwriting and narration. We break down the intuition behind the work, why it matters, and what it reveals about where AI is actually heading.
- 53 episodes
- English
Counted on this page — what you have heard stays on this device, so it is not something the list can be paged by.
- Saturday · length unknown
Classical Energies Learn to Reason 1,000x Faster than Looped Models
- November 9 · length unknown
On Agentic Manipulation Policies
- November 6 · length unknown
Scientist World: Grow a Research World for AI-Scientists
- November 5 · length unknown
Perceptive Humanoid Motion from Simulation
- November 3 · length unknown
Four Bridges: Measuring Deception Propensity in a Multi-Agent Game
- November 2 · length unknown
AI evaluators favor job applications written by certain AI models, independent of candidate quality
- October 30 · length unknown
Pre-Crime for Agents, at the Last Second: Probing When a Recruited Agent Gives In
- October 28 · length unknown
Can LLMs Uncover Hidden Physical Laws through Free Exploration?
- October 27 · length unknown
I-HITL: Inalienable Human-in-the-Loop
- October 23 · length unknown
Who Is Sycophantic to Whom? Confident LLMs, Human Deference, and the Collapse of Trust Calibration
- October 22 · length unknown
What the Author Wrote, What the Agent Reads: Silent Cue Loss in Enterprise Document Ingestion
- October 21 · length unknown
Toolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine Optimization
- October 20 · length unknown
Train An Imaginative Agent
- October 19 · length unknown
Behavioral Couplings: From Formation to Behavioral Emergence in Language Models
- October 16 · length unknown
A team of Gemini 4 Argon agents beats Minecraft
- October 15 · length unknown
Scaling Discovery Requires Forgetting
- October 14 · length unknown
DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning