Database

Revealing Latent Knowledge Through Personality-Shift Tokens

A research organization focused on reducing risks of astronomical suffering (s-risks) from advanced AI, with emphasis on conflict prevention and cooperation between transformative AI systems.

A scientific diplomacy organization working to improve global catastrophic risk governance in Spanish-speaking countries, with focus areas spanning AI regulation, pandemic biosecurity, food security, and risk management systems.

A 15,000+ page corpus on long-term interaction, symbolic language, unusual model behavior, and safety edge cases.

Seeking funding to secure API infrastructure and permanently eliminate the rate limits bottlenecking open-source EA grant evaluation.

Current LLM safety methods—treat harmful knowledge as removable chunks. This is controlling a model and it does not work.

No summary available yet.

No summary available yet.

Moving beyond Western-centric benchmarks to audit behavioral manipulation globally.

No summary available yet.

No summary available yet.

Studying more human-like intelligence through constraint-aware, curiosity-driven agents on ARC-AGI-3

Research agenda aimed at developing methods for constructing powerful, easily interpretable world-models.

No summary available yet.

I've been invited as I have contributed with input to prepare the meeting.

Funding to hire a junior researcher on a 3-5 month contract to help launch projects tackling existential risk

Epoch AI is a nonprofit research institute that tracks and forecasts the trajectory of artificial intelligence by analyzing trends in compute, data, algorithmic efficiency, and capabilities. It produces leading databases and quantitative models to help policymakers, researchers, and funders understand the pace and impact of AI progress.

Funding to hire an in-house entrepreneur on a 12 month contract to investigate a space within existential risk and then found an impactful project

No summary available yet.

Building a CPU-native AI architecture where meaning is geometric position, not statistical prediction. 27 experiments completed, 5 papers in draft.

AXRP is a podcast hosted by Daniel Filan featuring in-depth interviews with AI safety researchers about their published work and how it might reduce the risk of AI causing an existential catastrophe.

Fund unique approaches to research, field diversification, and scouting of novel ideas by experienced researchers supported by PIBBSS research team

Early-stage work on a small internal-control layer that tracks instability in LLM reasoning and switches between SAFE / WARN / BREAK modes.

New techniques to impose minimal structure on LLM internals for monitoring, intervention, and unlearning.

Our mission is to inform and organize the public to confront societal-scale risks of AI, and put an end to the reckless race to develop superintelligent AI.

Geoffrey Hinton & Yoshua Bengio Interviews Secured, Funding Still Needed

Making sure AI systems don't mess up acausal interactions

bridging the gap between tech industry and governments

One Month to Study, Explain, and Try to Solve Superintelligence Alignment

Helping charities drive policy change

Lionheart Ventures is a seed-stage venture capital firm investing in transformative artificial intelligence and frontier mental health technologies to mitigate civilizational risk.

CASCADE × AURA: Architectural AI Alignment Research

Original essays, videos on systemic alternatives to shift the Overton window, build cultural momentum for policies supporting long-term resilience & well-being

A Safety Framework for Evaluating AI Humanity Alignment Through Progressive Escalation and Scope Creep

Cryptographic attestation, runtime conscience, and an unfilterable kill switch. Live on the App Store and Google Play in 29 languages. AGPL, mission-locked

Persuading a critical mass of key potential influencers of Trump's AI policy to champion a bold, timely and proper US-China-led global AI treaty

Leaf runs online fellowships for exceptional teenagers (ages 15-19) to explore how they can have the most positive impact, including through a flagship course on AI safety called Dilemmas and Dangers in AI.

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

A public evidence package for testing whether LLMs only sound epistemically reliable

Deleted

Developing the software infrastructure to make AI systems safe, with formal guarantees

focused on 1. bci and wbe for safe ai, 2. cryptography and security for safe ai, and 3. safe multipolar ai

Funding to cover the first 4 month and relocating to San Francisco

GAP is an Australian charity, working to improve the long-term future, that requires funding for salary and operational expenses.

A 501(c)(3) nonprofit that accelerates neglected approaches to AI alignment by providing researchers with engineering teams, compute resources, and operational infrastructure.

A micro-project to turn an early AI governance prototype into risk notes, oversight checklist, review templates and public learning.

Siliconversations is a YouTube channel that creates animated videos explaining AI safety risks and existential risk from advanced AI to general audiences. It is run by a former quantum scientist who became a full-time content creator.

No summary available yet.

Making God is now raising for post-production so we can deliver a festival-ready documentary fit for Netflix acquisition.