The upcoming Alignment Jam #6 is about AI governance. With 6-8 specific cases to work from, you'll have the opportunity of a lifetime to engage with some of the major strategies to ensure that machine learning systems continue to be a positive technology for humanity!
Mechanistic Interpretability and Scalable Oversight
The latest two alignment jams from January and February 2023 were about mechanistic interpretability and scalable oversight! Participants reverse-engineered how neural networks understand information and developed novel ways to monitor AI with the guidance of our team and the wonderful Neel Nanda, Gabriel Recchia and Ruiqi Zhong. Check out the keynotes and winning presentations below!
🎥 1st 🏆 We Found " an" Neuron
🎥 1st 🏆 Automated testing of AI system deception
🎥 Keynote talk for Mechanistic Interpretability by Neel Nanda
🎥 Keynote talk for ScaleOversight by Gabriel Recchia
Hack away in teams to learn & have fun!
In-Person & Online
Join events on the GatherTown and Discord or at our in-person locations around the world!
Live Mentorship Q&A
Our central team will be available to help with any questions and theory on the hackathon Discord.
You can join in the middle if you don't find time and we provide code starters, ideas and inspiration; see an example.
Awards & Next Steps
We will help you take the next steps in your research journey; publishing, programmes, mentorship, etc.
Organize a local hackathon with help from us
The in-person hubs for the Alignment Jams are run by passionate individuals just like you! We organize the schedule, speakers, starter templates and funding, and you can focus on engaging your local research and engineering community. Click below and we will reach out to you.
See what our great hackathon participants have said
The hackathon was a really great way to try out research on AI interpretability and getting in touch with other people working on this. The input, resources and feedback provided by the team organizers and in particular by Neel Nanda were super helpful and very motivating!
Luca De Leo
AI Trends hackathon
I found the hackaton very cool, I think it lowered my hesitance in participating in stuff like this in the future significantly. A whole bunch of lessons learned and Jaime and Pablo were very kind and helpful through the whole process.
I was not that interested in AI safety and didn't know that much about machine learning before, but I heard from this hackathon thanks to a friend, and I don't regret participating! I've learned a ton, and it was a refreshing weekend for me.
A great experience! A fun and welcoming event with some really useful resources for starting to do interpretability research. And a lot of interesting projects to explore at the end!
Was great to hear directly from accomplished AI safety researchers and try investigating some of the questions they thought were high impact.