← Back to feed

My MATS 11.0 Application Experience

L5 · ResearcherTutorials & GuidesLessWrong AI· 8/26/2026

Provides insider perspective on elite AI safety fellowship applications for researchers pursuing alignment work.

AI Summary

An accepted MATS 11.0 applicant shares their experience with the OpenAI safety team stream application process and advice for future candidates.

Excerpt

Note: MATS Winter 2027 applications are open! You can apply here. If you're reading this later, you can check the main MATS page for information on upcoming cycles. I applied to MATS Autumn 2026 during this past summer, and was accepted into the OpenAI safety team stream. This post is about the application process, my experience applying, and my advice for future applicants. I would strongly recommend applying to MATS and other fellowships if you're interested in AI safety and want to make an im

Read Original
0 upvotes · 0 downvotes · 1 min read

Related Articles

L3 · BuilderTutorials & GuidesTowards Data Science
How to Work with AI Coding Agents

A practical guide on effectively using AI coding agents by providing context, breaking down problems, and maintaining control over the development process.

L4 · DeveloperTutorials & GuidesHugging Face Blog
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

Sentence Transformers v6.0 introduces a new MultiVectorEncoder model type, with a detailed guide for finetuning or training from scratch for late-interaction/ColBERT-style retrieval.

L3 · BuilderTutorials & GuidesHacker News
Serve Markdown to AI Agents with Accept Headers

Guide for serving Markdown content to AI agents via Accept: text/markdown headers to reduce token usage and improve RAG performance.

L4 · DeveloperTutorials & GuidesTowards Data Science
How Does a RAG Reranker Really Work?

Explains how RAG rerankers actually work at the token level rather than just architectural level, showing they learn statistical token associations conditioned on query-passage pairs.

L4 · DeveloperTutorials & GuidesTowards Data Science
Why Random Forest Needs to Be This Random

Explains the mathematical rationale behind Random Forest's feature subsampling, showing how it reduces correlated errors between trees beyond what bagging alone can achieve.