All episodes
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