Request for Proposals: Technical AI Safety Research

Request for Proposals: Technical AI Safety Research is sponsored by Open Philanthropy. A call for AI safety research with a broad remit to make grants that help the transition to transformative AI go well. The fund primarily supports early-stage work, with most grants aiming to reduce global catastrophic risks from advanced artificial intelligence.

Research areas include adversarial machine learning, exploring sophisticated misbehavior in LLMs, model transparency, trust from first principles, and alternative approaches to mitigating AI risks. Academic start-up packages for new academic labs are also supported.

Has Open Phil (or others) conducted a comprehensive analysis for both understanding and building the AI safety field? If yes, could you share some leads to add to my research? If not, would Open Phil consider funding such work?

(either under the above or other funds) Here is a recent example: Introducing SyDFAIS: A Systemic Design Framework for AI Safety Field-Building I'm new to applying for an AIS grant, so I have some common questions that might have been answered elsewhere: (1) what are some failure modes that I might need to consider when writing a proposal, specifically for a research project?

(2) will research expenses include stipends for the researchers? (3) can I write a grant to do a research project with my university AI safety group? I'm not sure if this will be considered a field-building or a technical AI safety grant.

Some common failure modes: Not reading the eligibility criteria Not clearly distinguishing your project from prior work on the topic you're interested in Not demonstrating a good understanding of prior work (would be good to read some/all of the papers we link to in this doc for whatever section you're applying within) Not demonstrating that you/your team has prior experience doing ML projects.

If you don't have such experience, then it's good to work with/be mentored by someone who does. "Research expeneses" does not include stipends, but you can apply for a project grant, which does. If you're looking for money to spend on ML experiments or to pay people who are spending their time doing ML research, then that may fall within this RFP.

If you're looking for money to do other things (e.g. reading groups, events, etc), then that may fall under the capacity-building team's RFPs.

Open Philanthropy Technical AI Safety RFP - $40M Available Across 21 Research Areas — EA Forum Open Philanthropy Technical AI Safety RFP - $40M Available Across 21 Research Areas Opportunities to take action Announcements and updates Opportunities to take action Announcements and updates Open Philanthropy is launching a big new Request for Proposals for technical AI safety research , with plans to fund roughly $40M in grants over the next 5 months, and available funding for substantially more depending on application quality.

Applications start with a simple 300 word expression of interest and are open until April 15, 2025.

We're seeking proposals across 21 different research areas, organized into five broad categories: Adversarial Machine Learning *Jailbreaks and unintentional misalignment *Backdoors and other alignment stress tests *Alternatives to adversarial training Exploring sophisticated misbehavior of LLMs *Experiments on alignment faking *Encoded reasoning in CoT and inter-model communication Evaluating whether models can hide dangerous behaviors Reward hacking of human oversight Applications of white-box techniques Finding feature representations Toy models for interpretability Interpretability benchmarks More transparent architectures Trust from first principles White-box estimation of rare misbehavior Theoretical study of inductive biases Alternative approaches to mitigating AI risks Conceptual clarity about risks from powerful AI New moonshots for aligning superintelligence We’re willing to make a range of types of grants including: Research expenses (compute, APIs, etc.) Discrete research projects (typically lasting 6-24 months) Academic start-up packages Support for existing nonprofits Funding to start new research organizations or new teams at existing organizations.

The full RFP provides much more detail on each research area, including eligibility criteria, example projects, and nice-to-haves. Please email [email protected] with questions, or just submit an EOI. Curated and popular this week Hard-to-reverse decisions destroy option value Stefan_Schubert · 9y ago · Curated 3d ago · 14 m read · 9y ago · Curated 3d ago · 14 m read This post is co-authored with Ben Garfinkel.

It is cross-posted from the CEA blog. A PDF version can be found here. Summary: Some strategic decisions available to the effective altruism m...

Introducing Impact List: a ranking of philanthropists by expected lives saved Elliot Olds · 4d ago · 6 m read TL;DR: I'm releasing a website that ranks philanthropists according to EA principles and research, and allows users to re-rank the list using their own assumptions. I'd like feedback and help making it better. I'd especially like ideas for how to make the results more trustworthy.

Funding may be available. Crossposted to LessWrong. Marginal Victories: career advising and opportunities for U.S. democracy preservation & political work Annika Burman 🔸 · 6d ago · 2 m read TL;DR: Marginal Victories is a new initiative to provide 1:1 career advising, opportunities, and resources for people exploring high-leverage U.S. democracy preservation and political work.

Built by impact-oriented people doing pro-democracy work, the early MVP is now up at marginalvictories. org. Fill out the 10-minute form now to receive these resources as they become available over the next few...

Recent opportunities to take action Job: Executive Director of CEEALAR (EA Hotel) CEEALAR · 18h ago · 3 m read Bentham's Bulldog · 1d ago · 3 m read Marginal Victories: career advising and opportunities for U.S. democracy preservation & political work Annika Burman 🔸 · 6d ago · 2 m read