The hackathon is happening right now! Join by signing up below and be a part of our community server.
.png)
Apart > Sprints
Reprogramming AI Models Hackathon
--
No items found.
Signups
--
No items found.
Entries
November 22, 2024 4:00 PM
to
November 25, 2024 3:00 AM
(UTC)
This event is finished. It occurred between
November 22, 2024
and
November 25, 2024
Project ideas:
- Feature phenomenology
- Discovering useful feature interventions
- Measuring feature intervention quality (when do feature interventions work well vs. fail)
- Understand how feature weight plays a role in intervention behavior
- Novel research
- Investigating auto-interp improvements
- Exploring jail breaking and elicitation techniques
- Interface
- Create interesting visualizations built off Goodfire SAE’s (e.g., feature map visualizations)
Resources
Hackathon participants will have access to:
- Goodfire’s SDK/ API with hosted inference
- Goodfire’s research preview playground
- TO DISCUSS: resources for general compute / openai or anthropic api calls (how much?)
Speakers & Collaborators
Tom McGrath
Chief Scientist at Goodfire, previously Senior Research Scientist at Google DeepMind, where he co-founded the interpretability team
Organiser
Dan Balsam
CTO at Goodfire, previously Founding Engineer and Head of AI at RippleMatch. Goodfire makes Interpretability products for safe and reliable generative AI models.
Organiser
Archana Vaidheeswaran
Archana is responsible for organizing the Apart Sprints, research hackathons to solve the most important questions in AI safety.
Organizer
📍 Registered jam sites
Beside the remote and virtual participation, our amazing organizers also host local hackathon locations where you can meet up in-person and connect with others in your area.
Register the first event below!
📣 Social media images and text snippets
No media added yet
No text snippets added yet
Submission Requirements
Each team should submit a research paper that includes:
- Project title and team members
- Executive summary (max 250 words)
- Introduction and problem statement
- Methodology and approach
- Results and analysis
- Discussion of implications for AI interpretability
- Conclusion and future work
- References
Additionally, teams should provide:
- A link to their code repository (e.g., GitHub)
- Any demo materials or visualizations (if applicable)
Evaluation Criteria
Submissions will be judged based on the following criteria:
- Interpretability Advancement
- Does the project contribute to the field of AI interpretability?
- Does it provide new insights into understanding or steering AI model behavior?
- How well does it align with the hackathon's focus on reprogramming AI models?
- Research Quality
- How original and innovative is the approach?
- Does it present novel ideas or combine existing techniques in unique ways?
- Do we expect the results to generalize beyond the specific case(s) presented in the submission?
- Technical Implementation
- How well is the project executed from a technical standpoint?
- Is the code well-structured, documented, and reproducible?
- How effectively does it utilize Goodfire's SDK/API and other provided resources?
- Presentation and Communication
- How clearly and effectively is the research presented in the paper?
- Quality of visualizations and demos (if applicable)
- Clarity of methodology explanation and results interpretation
No projects submitted yet! Add your project information in the form. We usually see projects submitted quite close to the deadline.
