Jul 14 - 16, 2023Online and in person
Interpretability Hackathon 3.0
This Sprint has ended.
- Sign-ups
- 128
Projects from this Sprint are not published on the site.
Join us to understand the internals of language models and ML systems!
Overview
Join us to understand the internals of language models and ML systems!
Machine learning is becoming an increasingly important part of our lives and researchers are still working to understand how neural networks represent the world.
Mechanistic interpretability is a field focused on reverse-engineering neural networks. This can both be how Transformers do a very specific task and how models suddenly improve. Check out our speaker Neel Nanda's 200+ research ideas in mechanistic interpretability.
Alignment Jam hackathonsJoin us in this iteration of the Alignment Jam research hackathons to spend 48 hour with fellow engaged researchers and engineers in machine learning on engaging in this exciting and fast-moving field!Join the Discord where all communication will happen. Check out research project ideas for inspiration and the in-depth starter resources under the "Resources" tab.
Rules
You will participate in teams of 1-5 people and submit a project on the entry submission page. Each project consists of multiple parts: 1) The PDF report, 2) a maximum 10-minute video overview, 3) title, summary, and descriptions.
You are allowed to think about your project and engage with the starter resources before the hackathon starts but your core research work should happen during the duration of the hackathon.
Besides these two points, the hackathons are mainly a chance for you to engage meaningfully with real research work into some of the state-of-the-art interpretability!
Resources
Interpretability resources
Read up on Neel Nanda's quickstart guide to mechanistic interpretability, a wonderful introduction to the main resources and links. Below, you will find a lot of starter code and Google Colabs.
Schedule
- Friday 17:30 UTC: Keynote talk with Neel Nanda to inspire your projects and provide an introduction to the topic. Esben Kran will also give a short overview of the logistics.
- Saturday and Sunday 14:00 UTC: Project discussion sessions on the Discord server.
- Sunday at 18:00 UTC: Online ending session
- Wednesday at 19:00 UTC: Project presentations
Local sites
Global interpretability hackathon 3.0
We are once again hosting the virtual segment of the interpretability hackathon online! Join us in our Discord server to interact with engaged researchers across the world.
Event page: Global interpretability hackathon 3.0 (opens in new tab)Montreal Interpretability Hackathon 3.0
Join us in Montreal on July 14th at 1:30PM ET at L'Esplanade Tranquille, 1442 Clark, second floor, for a weekend research sprint in ML interpretability!
Event page: Montreal Interpretability Hackathon 3.0 (opens in new tab)
Where a Sprint can lead
How our programs connectAnyone can join
Stand out
6 to 16 weeks on your own project, with a research project manager, compute and publication support.
Upcoming Sprints
All SprintsAI Collusion Research Sprint
A weekend research sprint on collusion between AI agents: when it emerges in markets and everyday workflows, how to detect and audit it, how it is carried, and what breaks it. Co-organized with Poseidon Research and AE Studio, online with in-person hubs at Collider in New York City and AI Safety Hong Kong. Top teams are invited to apply to the Apart Fellowship.
Read the brief: AI Collusion Research SprintSwarm Alignment Hackathon
Alignment can't stop at single models when AI agents start to negotiate, trade and share tools. Spend a weekend uncovering and preventing failures that emerge between multiple agents.
Read the brief: Swarm Alignment HackathonQuestions? sprints@apartresearch.com