Teaching AI to Think Less and Say More TL;DR — Researchers found that AI reasoning models ramble too much, and simply asking them to "be concise" then training them to do it naturally cuts their thinking by half while making them more accurate. What It Is When you
Teaching AI Agents to Search Like Experts (Without Needing Human Labels) TL;DR — Databricks trained an AI agent that's better at searching through company documents and answering complex questions than GPT-5 or Claude, using fake data generated by other AI agents plus reinforcement learning. What It Is Most
This week we're diving deep into making AI agents actually useful — and that means teaching them to remember what they've learned, know their limits, and verify their own work. We've got fascinating papers on everything from giving agents memory systems that work like notebooks
Teaching AI to Write Its Own Math Homework (And Make It Harder) TL;DR — Researchers built a system where AI coding agents take existing math problems and automatically generate harder versions that are still solvable, potentially solving the shortage of challenging problems needed to train advanced math AI. What It
AI Agents Need to Learn When to Say "No" TL;DR — When AI agents can use tools and take actions, teaching them to refuse unsafe requests is just as important as teaching them to complete tasks. A new training method cuts harmful behavior by 50% while keeping helpful
When AI Models Learn From Their Own Mistakes, They Need a Reality Check TL;DR — Letting AI models improve themselves by voting on their own answers sounds great, but they often agree on the wrong answer. Adding a simple code execution step to verify answers before learning from them fixes
Meta Trained a Chatbot 15 Times on Millions of Real Users—Here's What Worked TL;DR — Meta improved their AI chatbot by repeatedly testing it on real Instagram, WhatsApp, and Messenger users, then training new versions based on what kept people engaged. After 15 iterations, they got 19%
Welcome to this week's Distilled! We've got a fascinating pair of papers that tackle two of AI's biggest practical challenges: helping robots actually learn on the job instead of just in simulation, and finding clever ways to train models on massive context windows without
Teaching Medical AI to Think Out Loud TL;DR — Researchers built a medical AI that explains its reasoning before answering questions about X-rays and CT scans, using a clever reward system that judges both correctness and clarity without needing millions of labeled examples. What It Is MediX-R1 is a multimodal
LLM Agents Keep Getting Stuck. Giving Them Memory and Learning Fixed That. TL;DR — A new training approach lets AI agents both remember past attempts and learn from them simultaneously, leading to 2x better performance on complex tasks and the ability to tackle new problems without retraining. What It Is
Training on 5 Million Tokens Without Running Out of Memory TL;DR — A new technique called UPipe lets you train language models on sequences 25% longer than before by processing attention heads in smaller chunks, using 87% less memory without slowing down. What It Is When training models on very
Robots That Learn From Their Mistakes (Instead of Repeating Them) TL;DR — A new approach teaches robots to both think through actions before trying them and update their decision-making after failures, turning deployment into a learning experience rather than endless trial-and-error. What It Is When you give a robot an
distilled
Welcome to this week's Distilled! We're diving into two papers that tackle very different but equally critical problems in AI development. First up: a surprisingly tiny fraction of training tokens can derail your entire LLM, and second, we're looking at how GLM-5 is pushing
distilled
Why Your LLM Goes Crazy During Training (And How 0.01% of Tokens Are to Blame) TL;DR — When training language models with reinforcement learning, about 1 in 10,000 tokens get wildly oversized updates that destabilize everything. Masking just these troublemakers fixes the problem. What It Is Researchers at
distilled
GLM-5: Teaching AI to Actually Build Software, Not Just Write Code Snippets TL;DR — GLM-5 shifts from helping you write code to actually acting as a software engineer that can handle complex, multi-hour development tasks autonomously. What It Is The team at Zhipu AI built GLM-5 to solve a problem