Aug 24 - 26, 2023Online and in person
Distillation Write-a-thon 2.0
This Sprint has ended.
Projects from this Sprint are not published on the site.
Join us for the Distillation Writathon where you are tasked with writing more digestible versions of existing literature in AI safety research and theory!
Overview
Hosted by AI Safety Info in partnership with Apart Research

See the information document for up-to-date information on the event, e.g. how the top projects are selected.
You have multiple options for questions to attempt to distill!
- Pick a question from our idea sheet to work on
- Take one from the full list of questions on Coda, if it has a status of “Not started”, “In progress”, or “Bulletpoint sketch”
- Think of a new question (but first ask in the #distillation-hackathon channel on Discord if it’s a good fit for the site)
- Use a keyword to find another question already in the system. For example, if you want to see if there’s a question in progress about Cartesian frames:
- Go to aisafety.info
- Search for "cartesian frames"
- Click “I’m asking something else” when no live articles show up
- Click on the “edit” button next to one of the in-progress articles that show up to go to the doc
Other information
- If you write articles in the course of the write-a-thon, and if you write on Stampy in general, your contributions are released under a permissive copyright.
Resources
Get inspired for your own projects with these ideas developed during the reading groups!
Schedule
- Friday, August 25th, 7am UTC: Participants may start!
- Sunday, August 27th, 11pm UTC: Wrap-up Discord/GatherTown group call
Local sites
Factored Distillation @Equiano Institute
This is a Africa-wide hackathon, with main satellites in Cape Town, Johannesburg and Kenya.
Event page: Factored Distillation @Equiano Institute (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 SprintsThreat Intelligence & Threat Modelling Hackathon
Can LLMs scale up threat intelligence and threat modelling for AI data centres facing nation-state attackers? With Security Level 5 (SL5).
Read the brief: Threat Intelligence & Threat Modelling HackathonAgent Attribution Hackathon
Telling rogue AI agents apart from human-steered ones. One weekend to build attribution classifiers, simulate agents that evade them, and find rogue agents in the wild.
Read the brief: Agent Attribution HackathonQuestions? sprints@apartresearch.com