10th edition of AI Safety Camp

MATS Funding

Help us support more research scholars!

Help Apart Expand Global AI Safety Research

Incubate AI safety research and develop the next generation of global AI safety talent via research sprints and research fellowships

Exploring feature interactions in transformer LLMs through sparse autoencoders

Removing Hazardous Knowledge from AIs

Exploring novel research directions in prosaic AI alignment

3 month

Mapping neuroscience and mechanistic interpretability

Surveying neuroscience for tools to analyze and understand neural networks and building a natural science of deep learning

AI-Plans.com

AI Safety Serbia Hub - Office Space for (Frugal) AI Safety Researchers

Free/Subsidized/Cheap office space outside of EU but in good timezones with favorable visa policies (especially for Chinese/Russian but also other citizens).

Scoping Developmental Interpretability

6-month funding for a team of researchers to assess a novel AI alignment research agenda that studies how structure forms in neural networks

Apollo Research: Scale up interpretability & behavioral model evals research

Hire 3 additional AI safety research engineers / scientists

Translation of BlueDot Impact's AI alignment curriculum into Portuguese

Support to translate BlueDot Impact’s AI alignment curriculum into (Br) Portuguese to be used in university study groups and an online course

Compute and other expenses for LLM alignment research

4 different projects (finding RLHF alignment failures, debate, improving CoT faithfulness, and model organisms)

WhiteBox Research: Training Exclusively for Mechanistic Interpretability

1.9 FTE for 9 months to pilot a training program in Manila exclusively focused on Mechanistic Interpretability

Avoiding Incentives for Performative Prediction in AI

Joseph Bloom - Independent AI Safety Research

Trajectory Models and Agent Simulators

Cadenza Labs: AI Safety research group working on own interpretability agenda

We're a team of SERI-MATS alumni working on interpretability, seeking funding to continue our research after our LTFF grant ended.

Scaling Training Process Transparency

Compute and infrastructure costs

Activation vector steering with BCI

Build an AI Safety Lab at Oxford University

Funding to establish a safety and interpretability lab within the Torr Vision Group (TVG) at Oxford