The Reading Corner

ChatGPT-Augmented APR Fails to Generalize Unless You Feed the Right Clues

Automated Program Repair (APR) is supposed to save developers from doing the painfully slow work of hunting down and fixing...

Sep 22, 2026 0

Demographic Signals Survive Anonymization in German LLM Résumés

Hiring is getting a lot more automated—especially in the résumé stage. And while many teams focus on removing names and...

Sep 22, 2026 0

Talking “Nice” to the AI Doesn’t Mean It’s Cooperative—Here’s Why

Introduction: When your AI “gets” manners, but not the point Ever had a chat with an AI that sounds socially...

Sep 21, 2026 0

AI for Coding: Better Grades, Worse Memory, Less Ownership

=========================================================== Generative AI is showing up everywhere in student work—especially programming. New research from [the arXiv paper “Your Programming Students'...

Sep 21, 2026 0

Agentic Web Search: How Chatbots Decide, Query, and Attribute Facts

Conversational AI isn’t just “answering questions” anymore—it’s increasingly acting like a Web search agent , deciding when it needs the...

Sep 20, 2026 0

Universal set families for maximizing submodular & XOS

Imagine you’re trying to maximize a score over all subsets of items—except you’re only allowed to “look up” the score...

Sep 20, 2026 0

Design AI workflows that “fit” professional tasks, not just prompts

People love the idea that ChatGPT can “help with anything.” But new research from Ma and colleagues in [this paper](https://arxiv.org/abs/2609.16482)...

Sep 19, 2026 0

What Is Jev? TypeSafe AI's System One Model, Explained and Put to Work

Jev is TypeSafe AI's new System One model: instead of generating text, it takes the state of your system plus...

Sep 19, 2026 124

1/e Probability for Selecting the Best Pieces in Linear Matroids

==================== Introduction: The “secretary,” but for linear algebra rules If you’ve ever tried to make smart decisions while new information...

Sep 19, 2026 1

Submit Content