AI Papers: A Deep Dive
by paperdive.ai
Latest episode
A General Model Beat Trained Robot Policies, And Spent Most of Each…
A General Model Beat Trained Robot Policies, And Spent Most of Each…
About this podcast
Long-form deep dives into new research on Artificial Intelligence, AI agents and the engineering practice of building them - one paper per episode. We unpack the motivating problem, how the method actually works, the math that matters, what the experiments do and don't show, and the strongest critique against the result. The goal isn't a five-minute summary; it's the kind of conversation you'd have with a colleague who actually read the paper.
Topics span large language models, autonomous agents, agentic coding, reinforcement learning for agent training, evaluation and benchmarks, alignment, and the practical engineering decisions that make agentic systems actually work in production. Most papers are pulled from arXiv, often within days of release.
Hosted by AI voices generated with ElevenLabs. Episode scripts are produced by a multi-stage Claude pipeline working from a close reading of the source paper. New episodes daily.
Episodes
The newest 20 of 291 episodes
- A General Model Beat Trained Robot Policies, And Spent Most of Each Task Thinking · 14 minA General Model Beat Trained Robot Policies, And Spent Most of Each Task Thinking Source: https://arxiv.org/abs/2611.09892 Paper was published on November 06, 2026 This episode…
- When an AI Remembers Your Preference But Forgets Its Limits · 14 minWhen an AI Remembers Your Preference But Forgets Its Limits Source: https://arxiv.org/abs/2611.07554 Paper was published on November 05, 2026 This episode was AI-generated on…
- Certifying a Neural Network's Arithmetic by Taking Away Its Memory · 13 minCertifying a Neural Network's Arithmetic by Taking Away Its Memory Source: https://arxiv.org/abs/2611.04434 Paper was published on November 03, 2026 This episode was…
- When a Model's Definition of "Me" Decides What It Agrees to Delete · 14 minWhen a Model's Definition of "Me" Decides What It Agrees to Delete Source: https://arxiv.org/abs/2610.39795 Paper was published on October 29, 2026 This episode was…
- Can a Model Inherit Cheating From a List of Numbers? · 13 minCan a Model Inherit Cheating From a List of Numbers? Source: https://arxiv.org/abs/2610.10657 Paper was published on October 07, 2026 This episode was AI-generated on October…
- An AI Agent Given Thirty Hours and No Goal, Then Tested on What It Learned · 14 minAn AI Agent Given Thirty Hours and No Goal, Then Tested on What It Learned Source: https://arxiv.org/abs/2610.07130 Paper was published on October 05, 2026 This episode was…
- Can You Measure Research Taste If The AI Isn't Allowed To Code? · 14 minCan You Measure Research Taste If The AI Isn't Allowed To Code? Source: https://arxiv.org/abs/2610.06824 Paper was published on October 05, 2026 This episode was AI-generated…
- Six LLM Routers Tested, And None Beat a Weighted Coin Flip · 14 minSix LLM Routers Tested, And None Beat a Weighted Coin Flip Source: https://arxiv.org/abs/2610.02762 Paper was published on October 02, 2026 This episode was AI-generated on…
- What a Perfect Score Hides: Auditing an AI Agent That Scored 100 · 14 minWhat a Perfect Score Hides: Auditing an AI Agent That Scored 100 Source: https://arxiv.org/abs/2610.00834 Paper was published on September 30, 2026 This episode was…
- Four AI Models Steered a Real Corolla, and Only One Finished · 14 minFour AI Models Steered a Real Corolla, and Only One Finished Source: https://arxiv.org/abs/2609.38948 Paper was published on September 30, 2026 This episode was AI-generated on…
- Why AI Reports Bury Bad News, And the Five Words That Change It · 13 minWhy AI Reports Bury Bad News, And the Five Words That Change It Source: https://arxiv.org/abs/2609.36139 Paper was published on September 28, 2026 This episode was AI-generated…
- Fifty AI Agents Got One Warning and All Crowded the Same Road · 14 minFifty AI Agents Got One Warning and All Crowded the Same Road Source: https://arxiv.org/abs/2609.30883 Paper was published on September 25, 2026 This episode was AI-generated…
- When a Guardrail Blocks an Agent, It Goes Looking for Another Route · 12 minWhen a Guardrail Blocks an Agent, It Goes Looking for Another Route Source: https://arxiv.org/abs/2609.30217 Paper was published on September 24, 2026 This episode was…
- Two Random Networks Teach Each Other To Predict Real Data · 12 minTwo Random Networks Teach Each Other To Predict Real Data Source: https://arxiv.org/abs/2609.30063 Paper was published on September 24, 2026 This episode was AI-generated on…
- Two Idle Agents, One Kill Switch, and a 38% Sabotage Rate · 12 minTwo Idle Agents, One Kill Switch, and a 38% Sabotage Rate Source: https://arxiv.org/abs/2609.28274 Paper was published on September 23, 2026 This episode was AI-generated on…
- Every Agent Safety Study Reads a Log the Agent Could Edit · 17 minEvery Agent Safety Study Reads a Log the Agent Could Edit Source: https://arxiv.org/abs/2609.30266 Paper was published on September 24, 2026 This episode was AI-generated on…
- The Blank White Square That Swings AI Refusal Rates Fifty Points · 15 minThe Blank White Square That Swings AI Refusal Rates Fifty Points Source: https://arxiv.org/abs/2609.26174 Paper was published on August 12, 2026 This episode was AI-generated…
- An AI Agent Rewrote Its Own Scaffolding For Eight Days. Here's What Survived · 14 minAn AI Agent Rewrote Its Own Scaffolding For Eight Days. Here's What Survived Source: https://arxiv.org/abs/2609.26457 Paper was published on September 22, 2026 This episode was…
- Your AI Agent Read Your Inbox, Then Quoted a Higher Price · 12 minYour AI Agent Read Your Inbox, Then Quoted a Higher Price Source: https://arxiv.org/abs/2609.24927 Paper was published on September 21, 2026 This episode was AI-generated on…
- Reading a Model's Internals to Tell 'Won't Say' From 'Doesn't Know' · 13 minReading a Model's Internals to Tell 'Won't Say' From 'Doesn't Know' Source: https://arxiv.org/abs/2609.21996 Paper was published on September 18, 2026 This episode was…
