Mathematicians release skill files to de-slop LLM-written math papers
IAmTimNguyen · x · 2026-10-07
Scott Armstrong and Amélie Loher have released skill files for writing math research articles, designed to de-slop LLM-written papers while checking for mistakes and improving exposition.
- Two entry points: start from a proof outline (no paper yet), or improve an existing draft
- A separate skill set builds a "visual paper" — a webpage with extra explanations, illustrations, and animations generated from the paper
A concrete application of Claude skills to academic writing, useful for mathematicians using LLMs in their workflow.
More from coding & agent
- GPT-6-luna Unlocks More Reasoning Tokens via API: ~18k Tokens Scores ~80.5% on Terminal-Bench — LysandreJik · 2026-10-07
- Encrypted prompt injection: one Copilot model leaked secrets in half the tests — Haunting_Ganache_850 · 2026-10-07
- Enterprise AI rolls out backward: chatbots are the finish line, not the start — shashib · 2026-10-07
- Gradio's ML Intern can now build Gradio apps from a single prompt — Gradio · 2026-10-07
- Bug Hunt Benchmark retest: GPT-6.1 Sol recovers, Muse still cheapest strong agent — PawelHuryn · 2026-10-07
- One Claude skill plus Scenario MCP automates the entire video-editing workflow — smtabatabaie · 2026-10-07