Project
10-month funding to study ML at university and AIS independently
Led byPatricio Vercesi
Endorsed by
Database
Loading results...
Loading results...
Showing 401-450 of 692 results
Clear filters10-month funding to study ML at university and AIS independently
This grant provides a stipend for Cindy Wu to spend 4 months working on AI safety research.
One year stipend and compute budget, for full-time technical AI alignment research
Grant to attend ICLR 2024 for an accepted alignment related paper as an undergraduate student
AI Safety lab focusing on technical alignment and governance of AI in Africa and the Global South more broadly. We are a grassroots community-led research lab
Help us fund 2-3 new employees to support our team
An early-stage AI safety research group based in Sydney, Australia
6-month 1 FTE funding to train Multi-Objective RLAIF models and compare their safety performance to standard RLAIF
1-month pt. stipend for 4 MATS scholars working on autonomous web-browsing LLM agents that can hire humans + safety evals
Creating a fund exclusively focused on supporting AI Safety Research
Research (and self-study) project designed to map and offer preliminary assessment of AI ideal governance research
9 months support for an in-depth YouTube channel about AI safety and how AI will impact us all
Reach the university that trained close to 20% of OpenAI early employees
researching methods to continuously monitor and analyse artificial agents for the purpose of control.
Educational Scholarship in AI Alignment
6-month salary for continued work on shard theory: studying how inner values are formed by outer reward schedules
6-month salary to continue developing as an AI safety researcher. Goals include writing a review paper about goal misgeneralisation from the perspective of Active Inference and pursue collaborative projects on collective decision-making systems.
4-month stipend to continue AI safety projects
Literature review or other introductory material for Singular Learning Theory targeted at AI alignment applications
Combining "kickstarter" style functionality with transitional anonymity to decrease risk and raise expected value of participating in collective action.
AI safety research
6-month stipend for a small group of collaborators to continue research on the Agent Structure Problem
A 3-month fellowship in Cape Town, connecting a global cohort of talent to top mentors at MIT, Oxford, CMU, and Google DeepMind
Revealing Latent Knowledge Through Personality-Shift Tokens
6-month stipend to work on an ML safety project, with the aim of joining a ML safety team full-time after
6-month salary to develop tools to test the natural abstractions hypothesis
A directory within AISafety.com that consolidates free guidance calls from AI safety advisors, helping newcomers identify how to contribute most effectively to the field.
Enabling prosaic alignment research with a multi-modal model on natural language and chess
A 15,000+ page corpus on long-term interaction, symbolic language, unusual model behavior, and safety edge cases.
6 months of independent alignment research and upskilling
AI safety dinners
A small, short workshop focused on coordinating/planning/applying «boundaries» idea to safety
Two workshops on strategic communications around AI safety, focused on the AI safety community
6-month salary to produce 2 AI governance white papers and a series of case studies, with additional research costs
This grant will support Viktor Rehnberg's project identifying key steps in reducing risks from learned optimisation and working towards solutions that seem the most important. Viktor will start working on this project as part of the SERI MATS program.
Research on the links between short- and long-term AI policy while skilling up in technical ML
Seeking funding to secure API infrastructure and permanently eliminate the rate limits bottlenecking open-source EA grant evaluation.
No summary available yet.
Funding for 3 months independent study to gain a deeper understanding of the alignment problem, publishing key learnings and progress towards finding new insights.
1.5 year stipend for thorough investigation and analysis of AI lab scaling policies
Current LLM safety methods—treat harmful knowledge as removable chunks. This is controlling a model and it does not work.
No summary available yet.
7 months of coworking-space funding continuation, during interpretability research project
Support to cover the costs of leaving employment in order to pursue AI safety research.
20 Weeks Salary to reach a neglected audience of 10M viewers
We're a team of SERI-MATS alumni working on interpretability, seeking funding to continue our research after our LTFF grant ended.
Make 12 more AXRP episodes
No summary available yet.
No summary available yet.
Moving beyond Western-centric benchmarks to audit behavioral manipulation globally.
