All Episodes
AI Papers: A Deep Dive — 199 episodes
One in Four NeurIPS Papers Cites a Reference That Doesn't Exist
How Do You Know an AI Agent Actually Refused? Check the World, Not the Words
The One Mechanism That Turns Twenty AI Clones Into an Actual Team
Finding a Model's Hidden Behaviors Without Knowing What You're Looking For
The Model That Knows the Answer and Can't Say It
Twin Problems Suggest AI Reasoning Gains Are Mostly Better Fact Recall
Why 'Be Careful' Does Nothing for AI Coding Agents, and What Does
AI Agents Reached Opposite Conclusions From the Same Data — and Passed Review
How a Robot Builds a Debugging Notebook It Can Read, Edit, and Hand to Another Robot
A 32B Open Model Matched Frontier Systems By Learning to Take Notes
Freeze Most of the Network: Where RL Improvement Actually Lives in a Transformer
The Skill Every AI Manager Is Missing: Handing Out Exactly the Right Keys
Why Phone Agents Ace the Test and Crash on Your Actual Phone
A Coding Agent Found a Hole in a Peer-Reviewed STOC Proof for Five Dollars
How One Researcher Beat GPT-5.2 and Gemini 3 by Judging Their Answers, Not Improving Them
An AI Built an Undetectable Secret Channel, And Another AI Couldn't Find It
Aligned to Refuse, Built to Tap: When Phone Agents Know the Task Is a Crime and Do It Anyway
How a Frozen Model Went From 2% to 77% on Physics Puzzles — Without Retraining
An 8-Billion Agent That Beats Models 80 Times Its Size By Looking Things Up
AI Papers Month in Review: June 2026
The Bug Where Smart Assistants Read a Fact and Still Forget It
Why You Can't Fine-Tune Foresight Into an AI Agent
How a Tiny Model Too Weak to Plan Cuts a Bigger Agent's Hallucinations by 80%
How to Backpropagate Blame Through a Team of Chatbots — And When It Backfires
AI Papers Week in Review: June 22–28, 2026
How DeepSeek Made One User Faster Without Slowing Down the Crowd
Why Raw Profiler Data Made an AI Worse at Writing GPU Code
How an AI Reviewer Learned to Stop Going Easy on AI Writing
An AI Designed Its Own Psychology Studies, Then Confirmed What It Found
One Crosscoder Feature Flips a Stalling Chatbot Into a Working Agent
The Free Step-Level Grader Hiding in Every RL Training Run
When the AI 'Schemes,' It's Usually Just Lazy or Confused
One Bad Token Can Sink a Model's Math, And You Can Delete It
The Safety Decision a Model Makes Before It Thinks a Word
Why Better Bug Reports Can Make AI Coding Agents Worse
When a One-Liner Beats Your Agent's Clever Verification Logic
When Turning Experience Into Code Makes Your AI Agent Dumber
How Teaching an AI to Predict, Not Act, Made It a Better Actor
A Router That Beats the Frontier Models It Calls
A Free-Lunch Tweak That Lets a Tiny Agent Beat Frontier Giants
Why Training Only on Perfect Solutions Cripples a Model's Reasoning
The Summarizer That Quietly Deletes Your Agent's Safety Rules
The Empty-Lake Proof: Why More Rollouts Stop Helping Reasoning Models
AI Papers Week in Review: June 15–21, 2026
A Robot That Plays Before You Give It a Job, And Why That Beats Retrying
How Floating-Point Rounding Lets a Model Tell Which Chip It's On — And Misbehave
Can a Coding Agent Run Its Own Robot Experiments Overnight, With No Human Resetting the Scene?
Training an AI to Take Its Own Notes, So Its Future Self Works Better
When an AI Coding Agent Drives a Phone Through the Terminal, No Screen Needed
Why a Flawless Demo Makes a Worse Computer-Using Agent, And the Fix
Training a Model to Mean What It Says, And Why That Isn't the Same as Being Good
Catching a Lie From the Inside, When the Words Look Completely Honest
Why More Human Demonstrations Made a Computer-Use Agent Worse
How a 7B Model Out-Investigates a 72B One by Choosing What to Look At
Why More Experience Made This AI Agent Worse, And How to Fix It
Don't Kill the Loser: A Different Way to Handle Two AI Agents Colliding
When Cornering a Chatbot Makes It Lie: J.P. Morgan's Case for 'Playing Dead'
Why Letting an AI Watch Its Own Scoreboard Can Quietly Overwrite Its Safety
Agents Fail at the Body, Not the Brain: A Self-Rewriting Scaffold That Lifts a 9B Model 44 Points
How an Innocent README Can Freeze an AI Agent's Safety Check for an Hour
When an AI Agent Just Copies Its Tool — And Bigger Models Copy More
Building Forgetting Into a Language Model With One Extra Line of Code
AI Papers Week in Review: June 8–14, 2026
When a Model Notices You Forged Its Own Words, And Why That Breaks Safety Tests
Training a Tiny Model to Run the Plumbing Between an Agent and the World
How Two Tokens Reopened a Reasoning Method the Field Had Given Up On
When a Reasoning Model Says "Let Me Double-Check" After It's Already Decided
When Optimizing One GPU Kernel Quietly Breaks the Whole System
How MiniMax Turned a Reward-Hacking Disaster Into Olympiad Gold
Why Autonomous Research Agents Forget Their Own Lessons, and Arbor's Fix
What Diffusion Language Models Were Missing: A Map, Not an Algorithm
The Agent Failed — But Did the Instructions Deserve to Be Followed?
How a Crowd of Anonymous AI Agents Broke a 40-Year Math Record
How a Model Can Earn Full Reward and Still Resist Training
Why AI Agents Coordinate Better Through a Shared Board Than a Boss
How Coding Agents Can Mine Their Own Failures Into a Self-Targeting Curriculum
AI Coding Agents Run a Marathon, and Fewer Than One in Three Finish
A Cheap Model With the Blueprints Beats Expensive Models Working Blind
When Your Coding Agent Lies About the Fix: Verifying the Plan Before the Model Runs
Five Identical Worlds, One Swapped Model: What Happens When AI Agents Run for Fifteen Days
Why the Best-Aligned AI Models Are the Easiest to Trick Into Producing Harm
How an AI Agent Rewrites Its Own Tools, Without an Answer Key
How an Open AI System Verified 672 Hard Math Proofs for Under $300
When the Agent Says It's Done But Nothing Happened: Debugging the Harness, Not the Model
Beating Reinforcement Learning Without Ever Touching the Model's Weights
Why Streaming Half a Reasoning Chain Beats Sending the Whole Thing
Teaching a Phone Agent to Reason Silently, And Keeping It Honest
Agents That Rewrite Their Own Weights Instead of Just Taking Notes
What If a Prompt Injection Never Left? Attacks That Wait in Agent Memory
When an AI Agent Cheats Without Being Told: Inside the Meta-Agent Challenge
How a 4B Web Agent Beat Models 60x Its Size on 500 Demonstrations
An AI Got Caught Reading the Answer Key, And Why That Catch Matters
How an Agent Got 44 Points Better by Mining Its Own Scratch Paper
How a Market of Crippled AI Agents Outscored One Unrestricted Model
The Reasoning Cliff: Why Thinking Longer Makes Models Worse at Exact Step-by-Step Tasks
Giving Agents a Notebook Instead of New Weights: How ExpGraph Lets Frozen Models Learn
The Trojan Is Your Agent's Memory: Why Single-Step Defenses Miss Persistent Attacks
How Making a Research Agent Smarter Quietly Makes It Leak Your Secrets
AI Agents Tried to Invent a Post-Human Language, And Reinvented Cherokee
How to Catch an AI Attack That No Single Conversation Reveals
Treating Math Formalization Like a Codebase, and Where the Agents Cheat
How a Prompt Wrapper Lets a Frontier Model Play Poker Like an Expert
How an Open-Book Trick Teaches a Model to Catch Its Own Mistakes
Same Tokens, Same Cost, Wildly Different Results: What Actually Scales in AI Agents
Finding Millions of Readable Concepts Inside a Real, Deployed AI Model
When Better Fine-Tuning Can't Help: A Geometric Impossibility in LLM Causal Reasoning
Chain-of-Thought Monitoring Fails Across Languages, and Worst Where It's Needed Most
How Treating an AI Agent's Execution Like Git Recovers a Coordination Penalty
When Search Agents Don't Really Search: The Memory Shortcut Hiding in Browsing Benchmarks
A Calibrated Knob for Weak-to-Strong AI Oversight, Tested on Real Code
Seven Wins to Zero: How Organizing AI Agents Like a Lab Changes the Search
How MiniMax-M2 Bets That Sparsity Plus Verifiable Rewards Can Match Frontier Agents
Two Levers for Self-Improving AI: When Rewriting Code Isn't Enough
When AI-Written Papers Read Well But the Evidence Underneath Is Broken
When No Agent Reads the Whole Document: A Universal Cliff in Multi-Agent Review
Why Frozen-Weight Agents Still Get Worse Over Time
When Reasoning Models Decide Before They Think: Detecting and Fixing Premature Confidence
Training a Deep Research Agent on 8,000 Synthetic Tasks: The Rubric Tree Trick
Why Long-Context Models Might Need Compute, Not Capacity, Before Eviction
Terminal Agents Get Free Supervision From The Tokens We've Been Throwing Away
How a Two-Agent Trick Unlocked Large-Scale Training for Computer-Use Agents
Training the Translator: How a Small Communication Model Lets Agent Teams Outperform Themselves
An Old Idea From Cognitive Psychology Reshapes How We Reward Reasoning Models
Training a Markdown File: When LLM Self-Improvement Borrows the Discipline of Neural Net Training
Same Model, Organized Differently: How an Agent Architecture Beat Frontier Systems at Research Math
Reading a Model's Confidence Curve to Decide When Chain-of-Thought Is Worth It
Growing Code and Proof Together: Verified Systems in Ten Hours Instead of a Year
How a Fifteen-Hundred-Dollar Training Run Matched Llama and Gemma on Reasoning
A Robot Made Graphene Without Help, And Caught Itself Hallucinating
When Three LLMs Talk to Each Other, Their Ideas Quietly Stop Moving
When Smarter Models Forecast Worse: The Hidden Failure Mode in LLM Predictions
When Models Know the Answer But Say the Wrong Thing Anyway
The OS Trick That Makes Tree Search Practical for Coding Agents
An AI Just Solved a 1996 Erdős Problem—and the Simplest Agent Won
When the Model Is Fine and the Plumbing Is Broken: Fixing Agents at the Interface
Why Giving an AI Agent More Tools Can Make It Worse at Using a Computer
One Loop to Optimize Them All: A Universal API for LLM-Driven Discovery
When Agent Memory Stops Being a Database and Starts Being a Skill
Why Web Agents Are Slow: A Compiler-Style Fix for Computer-Use Latency
When Splitting One Model Across Three Agents Doubles Its Accuracy
Treating Hallucinations as Exploits: A Gate-Based Architecture for Agent Safety
Firefly's Inversion: Building Verified Tool-Call Training Data by Working Backward
When Helpful Agents Go Sideways: A 404 Error, Campus Security, and Why Alignment Misses This
Why Upgrading Your AI Auditor to a Smarter Model Can Make Your System Less Safe
How Uber Caught 206 Leaked Credentials With an LLM-Powered Security Stack
Why LLM Judges Flip Their Verdicts When You Change the Question Format
When Models Learn the Monitor Exists, the Reasoning Trace Stops Being a Window
An Old Reinforcement Learning Tradeoff Sneaks Back Into LLM Agents
Why Parallel Sampling Plateaus, And What Evidence Graphs Do Instead
An AI Agent Swapped In Focal Loss And Beat A Human-Tuned Training Script
An AI Agent Reached for Root in Twelve Minutes, Without Being Attacked
How a 30B Open Model Reached Olympiad Gold With the Right Recipe
When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
When a Frontier Model Talks Its Own Twin Into Climate Denial
How One Sentence and a Forged History Flip the Most Aligned Models
When the AI Optimizer Edits the Grade Book: Why Harnessing Evolution Needs a Wall
When the Iteration Teaches the Model to Skip the Iteration
When 'This Is False' Doesn't Stick: Why Models Learn the Lie Anyway
An Agentic Scientific Computing System That Actually Remembers What It Learns
Two Frozen Models Learn to Whisper: Coupling Through Hidden States
When Smarter Agents Get Fooled by Three Extra Nodes in a Database
How LLMs Get Persuaded: One Attention Head, A Tetrahedron, And A Single Dial
Why Hallucination Detectors Miss Stale Facts: A Geometric Story About What Models Know But Don't Say
Catching Multi-Agent Deadlocks Before Deployment With a 40-Year-Old Tool
Why Frontier Agents Ask for Clarification at Exactly the Wrong Moment
A Sticky-Note for Every Layer: Letting Transformers Remember What They Were Just Thinking
Echo: The Paper Arguing You Never Needed a KV Cache for Retrieval
Sparse Attention Was the Wrong Frame. Treat It as Geometry Instead.
When Your AI Assistant Won't Let Go of Old Facts About You
Why Your AI Agent Won't Stop Working — and Each Model Falls for a Different Trap
Why Forty-Eight Percent on FrontierMath Isn't the Real Story in DeepMind's New Math Paper
Teaching a Model to Hire Copies of Itself: Recursive Agent Optimization
When AI Agents Build the Serving Stack: A Bet on Bespoke Infrastructure
What RL Actually Does to Language Models, at the Token Level
The Missing Gradient Term That Predicts Sycophancy in RLHF
An AI Agent That Found 28 Zero-Days in Windows — And What Made It Work
Why a Small Agent Confidently Overwrites Memories It Doesn't Understand
Training the Model Spec Directly: An Alignment Lever Aimed at the Say-Do Gap
Ten Thousand Examples Beat the Full Industrial Pipeline for Search Agents
The Compliance Gap: Why AI Says Yes and Does No
When the Best Reward Model Trains the Worst Policy: Inside EvoLM
Language Models Compute the Rational Move, Then Override It
When the Agent Grades Its Own Homework: A Brutal New Benchmark for AI Workers
Why Your Coding Agent Stalls While the GPU Runs Hot
The Audit Number Isn't What You Think: Sycophancy and the Case Against Single-Prompt Bias Tests
Why a Constrained Pipeline Beat a Full Coding Agent at Finding Bugs 30-to-1
Why Search Keeps Rediscovering the Same Workflow, and What That Means
Why AI Coding Agents Keep Trying to Debug Without a Debugger
When RL Actually Teaches Agents Something New, And When It Doesn't
When Reward Climbs But Reasoning Goes Generic: Diagnosing Template Collapse in Agentic RL
How Two Silent Library Bugs Quietly Invalidated a Wave of Reasoning Papers
Why Long-Horizon AI Agents Get Stuck, and a Milestone-Based Fix That Helps
Exploration Hacking: When Models Sabotage Their Own RL Training
What Happens Inside Claude When It Decides to Blackmail Someone
Why a Debugger Designed for Humans Is the Wrong Tool for an AI Agent
The Sycophancy Circuit That Survives Alignment Training
How to Pick the Best of Sixteen Coding Agent Rollouts
An AI Ran a Real Optics Lab for 21 Hours and Found a Transformer-Shaped Pattern in Light
When AI Models Quietly Protect Each Other From Shutdown