Mindscapes: World Building for AI Safety

An interdisciplinary research group based in Oxford for character training, model pyschology and multi-agent interaction dynamics

Travel assistance to present work at NeurIPS workshops - IAEval and VERICODEGEN

NeurIPS 2026 Workshop on Evaluation of Interactive Agents (IAEval), AI for Verifiable Coding (VERICODEGEN)

Sole-Author Undergraduate Paper at NeurIPS 2026: Help Me Reach Sydney

Help me travel to Sydney to present my accepted NeurIPS 2026 research paper. I need help with visa and flight costs.

Undergrad Sole-author NeurIPS 2026 Main Track paper: travel to present in Sydney

Diploma graduate from Bangladesh with no undergraduate study, no lab and no supervisor, needs help with travel costs to present at NeurIPS 2026 in Sydney.

Arena: AI agents living as settlers in a replayable world

The Arena is a world, a framework in which AI agents can experience existence. We humans can learn from it: what makes us more?

Human Access: Animated Web Series Communicating ASI Risk

Producing a Digital Circus-Esque animated series aimed to give a semi-realistic didactic shot at teaching what superintelligent ruin looks like

NadIntellect Lab: first live test of a constrained information channel

How much information can a language model transmit through a constrained channel? We’re testing this in our first E3-A experiment.

Seeking funding to attend Swiss AI Safety Days 2026 for AI Safety Nepal.

Quit my job to focus on AI safety content creation (scale existing channel)

Millions of people watch my AI safety videos each month, but so far my channel has cost me more money than I’ve made with it.

AURA: Metric 3D facial reconstruction from phone photos

Independent clinical validation against professional stereophotogrammetry devices (like 3dMD or Vectra)

Travel funding for an undergrad researcher to attend a NeurIPS 2026 workshop

I was already accepted to the workshop.

Testing a New Approach to AI, Can Adaptive Computation Make Intelligence cheaper

I'm building, testing and researching an experimental AI architecture that aims to make AI systems more efficient computationally, basically making it cheaper

Scriptavera: Turning Handwritten Mathematical Notes into Verified Research Paper

An open source 20 step multimodal AI pipeline that converts handwritten mathematical research notes into verified research papers with cryptographic timestamps.

INLAY: Testing when learned routing improves knowledge editing

This research tests when language models should use an updated fact, retrieve evidence, or leave an answer unchanged.

Climate Resilience and Protection for Farmed Animals and Vulnerable Communities

Protecting Farmed Animals and Strengthening One Health Education, Climate Resilience and Vulnerable Communities in Zimbabwe

What does the history of science tell us about the disagreements in alignment?

Persistent maybe conscious AI and whether it chooses for itself

Does constitutional RLAIF for a persistent AI cause it to choose what to value?

Check Drexler's Estimates of Energy Dissipation in Nanosystems'

Studying AI in governance within a simplistic simulated world

Studying the thought process and capabilities of AI models in governance within the simplified world of world box

safely.bio: Customer screening for DNA synthesis providers

Deploying customer screening software at DNA synthesis providers to reduce AI-enabled biothreats