distilled

Distilled Weekly — Feb 16 - Feb 22, 2026

Santthosh Selvadurai

22 Feb 2026 — 1 min read

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 beyond autocomplete-style coding to actually building complete software systems.

This Week's Papers

1. Why 0.01% of Tokens Are Breaking Your LLM Training (And How to Fix It)

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.

2. GLM-5: Teaching AI to Actually Build Software, Not Just Suggest Code

GLM-5 shifts from helping you write code to actually acting as a software engineer that can handle complex, multi-hour development tasks autonomously.

That's a wrap for this week. Hit reply if any of these sparked an idea.

— Santthosh

Teaching AI to Think Out Loud Without the Rambling

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 to Search Like a Pro: How Reinforcement Learning Created a Next-Gen Enterprise Search Agent

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

Distilled Weekly — Mar 02 - Mar 08, 2026

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

Can AI Agents Create Harder Math Problems By Writing Code?

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