Project
Conducting independent research into AI forecasting and strategy questions
Led byTegan McCaslin
Endorsed by
Database
Loading results...
Loading results...
Showing 101-150 of 690 results
Clear filtersConducting independent research into AI forecasting and strategy questions
Support to conduct a research project collaboration on Compute Governance
Research into the international viability of FHI's Windfall Clause
Collective intelligence systems, Mechanism Design, and Accelerating Alignment
No summary available yet.
No summary available yet.
Retrospective support for small virtual reading group on AI safety topics
Enabling rapid deployment of specialized engineering teams for critical AI safety evaluation projects worldwide
Retrospective funding of salary for up-skilling in infrabayesianism prior to start of SERI MATS program
Research to enable transition to AI Safety
Stanford Artificial Intelligence Professional Program tution
4 month salary to support an early-career alignment researcher, who is taking a year to pursue research and test fit
6-month support for self study and development in ML and AI Safety. Goals include producing an academic paper while working on the "Inducing Human-Like Biases in Moral Reasoning LMs" project run by AI Safety Camp.
Identifying operational bottlenecks and cruxes between alignment proposals and executable governance.
6-month salary to upskill for AI safety
Translating an AI safety report (1k+ downloads) for peer-reviewed publication to formalize "Emergent Depopulation" as a novel systemic risk.
work title: Seductive Machines and Human Agency
No summary available yet.
6-month salary to work on the research I started during SERI MATS, solving alignment problems in model based RL
6-month salary for self-study to be more effective at AI alignment research
2-year funding to run public and expert surveys on AI governance and forecasting
One-year full-time salary to work on alignment distillation and conceptual research with Team Shard after SERI MATS
Operational Support for a Pilot Study on Complexity Modelling, Expert Judgement, and Deliberative Democracy for Risk Prioritization and Mitigation
Measuring attack selection as an emergent capability, and extending offensive cyber time horizons to newer models and benchmarks
Teleology, agential risks, and AI well-being
Financial support to help productivity and increase time of early career alignment researcher
3-month stipend for upskilling in AI Safety and potentially transition to a career in Alignment
6 months salary for independent work centered on distillation and coordination in the AI governance & strategy space
6-month salary plus expenses for Jay Bailey to work on Joseph Bloom's Decision Transformer interpretability project.
No summary available yet.
No summary available yet.
Theory of change, i.e. 'How does this work reduce existential risk from advanced AI?' AISafety.com is a field-building project that aims to multiply global AI safety efforts through a centralized…
No summary available yet.
Build a theory of abstraction for embedded agency using real-world systems for a tight feedback loop
Runway for the core staff to design the program, find mentors and get funding
6-month salary to verify neural network scalably for RL and produce a human to super-human scalable oversight benchmark
Development of mathematical language for highly adaptive entities (having stable commitments, not stable mechanisms)
No summary available yet.
6-month salary to research AI alignment, specifically the interaction between goal-inference and choice-maximisation
12-month salary for independent research, upskilling, and finding a stable position in AI-Safety
1-year salary and costs to connect, expand and enable the AGI governance and safety community in Canada
8-month salary to work on technical AI safety research, working closely with a DPhil candidate at Oxford/FHI
I self-funded research into a new threat model. It is demonstrating impact (accepted at multiple venues, added to BlueDot's curriculum).
Replacing reduction in income due to moving from full- to part-time work in order to pursue an AI safety-related PhD
10-month salary for research on AI safety/alignment, scaling laws, and potentially interpretability
Compute Funding
1-year stipend and compute for conducting a research project focused on AI safety via debate in the context of LLMs.
No summary available yet.
6-month stipend to work on AI alignment research (automated redteaming, interpretability)
No summary available yet.
