Hear what a few of the organizers have said:

• Carolina Oliveira, Condor Camp, São Paulo
  It was an amazing experience! The participants are very engaged, and the problems set by the Apart team make it fun and with a broad scope of action for everyone. 11/10 would do it again.
• Abhay Sheshadri, Georgia Tech, USA
  It felt great to enable smart, motivated people to work on alignment-related research. I mostly focus on technical work, but I have been pondering how much more effective I could be if I worked on getting new people to join the field. The hack allowed me to feel a bit of that, which I think could be a useful experiment to, on a small scale, test your fit with AI safety community-building.
• Mykyta Baliesnyi, Tallinn University, Estonia
  It was fun, getting all our members rallying around a singular objective. I think this event has just brought a lot of people closer to the club, even if most of us didn't end up submitting our work. I think we have a better idea of what to expect from future interpretability hackathons, and what areas we need to skill-up in. The act of hosting wasn't too demanding, and I would love to do it again.

The research hackathons also always result in very impressive research for how long participants have during the weekend! Of course, organizers and participants should temper their expectations, but the ambitious projects might look like these:

• Relating induction heads in Transformers to temporal context model in human free recall
• Seemingly Human: Dark Patterns in ChatGPT
• We Discovered An Neuron
• EscalAtion: Assessing Multi-Agent Risks in Military Contexts

You can also see the ones that were published at peer-reviewed academic venues on the Sprints front page. Really amazing work!And of course, read more about how you can host a location on our organizer guide.