AI Futures Project
Led byJonas Vollmer
Database
Loading results...
Loading results...
Showing 251-300 of 691 results
Clear filtersAI Futures Project
Independent collective. Φ-Arena open benchmark, 3 ICLR 2027 papers (Φ-Arena, mechinterp, energy-bounded) — kickstart for a 10-year program.
No summary available yet.
Non-profit facilitating progress in AI safety R&D through events
No summary available yet.
Retroactive grant to study Goodhart effects on heavy-tailed distributions
~4 FTE for 9 months to fund WhiteBox Research, mainly for the 2nd cohort of our AI Interpretability Fellowship in Manila
4-month stipend for a career transition period to explore roles in AI safety communications
Short Documentary and Music Video
Support for alignment theory agenda evaluation
3 month salary for AI safety work on deconfusion and technical alignment.
1-year stipend (and travel and equipment expenses) for support for work on 2 AI safety projects: 1) Penalising neural networks for learning polysemantic neurons; and 2) Crowdsourcing from volunteers for alignment research.
A Coherence based Emergent Protocol
My basic approach is to divide the problem into several cases, focusing specifically on situations in which an AI can modify its own reward system. The first distinction is between tampering with…
Practicing Embodied Protocols that work with Live Interfaces
1.5-month salary to write a paper/blog post on cognitive and evolutionary insights for AI alignment
No summary available yet.
1-year salary for independent research to investigate how LLMs know what they know.
Enabling Compassion in Machine Learning (CaML) to develop methods and data to shift future AI values
A virtual pet simulator that teaches reinforcement learning failures through simple and fun interactions.
2-month salary to test suitability for technical AI alignment research and identify a research direction
6-month stipend to remove conditional bad behaviors from LLMs via a learned latent space intervention
No summary available yet.
5-month salary and compute expenses for technical AI Safety research on penalizing RL agent betrayal
6-month stipend to continue independent interpretability research
2 months of part-time salary for a trial + developer costs to maintain and improve the AI governance document sharing hu
No summary available yet.
Ship It: Building Bridges for Better AI Outcomes
3-month salary for SERI-MATS extension
Create a value learning benchmark with contextualized scenarios by leveraging a recent breakthrough in natural language processing
12-month salary to work on alignment research!
Developing noise-injection methods to reveal and reduce deceptive behaviors in language models prior to deployment
4-month expenses for AI safety research on personas and sandbagging during the MATS 5.0 extension program
1-year stipend to make accessible-yet-rigorous explainers on AI Alignment/Security, in the form of games/videos/articles
6-month salary for an AISC project and continuing independent mechanistic interpretability projects
An advanced agent that perceives your screen and executes tasks by controlling the mouse, acting as a digital proxy to handle complex work on your behalf.
12-month salary for researching value learning
General support of research led by David Lorrell
No summary available yet.
pushing bounds of organized digital systems
4-month funding for independent alignment research and study
General Support for an AI Safety evals for-profit
No summary available yet.
Empirical measurement infrastructure proving whether AI systems hold their constraints under real operating conditions.
6-month stipend to continue research on benchmarks for interpretability and on characterizing Goodhart's Law
9-week stipend for two part-time researchers to write and publish a policy proposal: Mandatory AI Safety ‘Red Bonds’
4M+ views on AI safety: Help us replicate and scale this success with more creators
≤1-year salary for alignment work: assisting academics, skilling up, personal research and community building
No summary available yet.
No summary available yet.