Mindscapes: World Building for AI Safety

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

Depth or Length? How Looped LLMs Trade Hidden Loops for Visible Reasoning

GPU funding to finish my research of looped language models. Early tests show extra loops replace reasoning length.

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?

Travel Grant: SDNTS Neuroscience School in Uruguay

JARVIS: An self-evolving Mixture-of-Experts (MoE) LLM-An Auditable Research Loop

It evolves its own architecture, it picks its own next step, tries changes to its own design: adds layers and experts, trains the child (wider context)

Inline activation control for LLM serving in vLLM

Moving a working geometric pressure-reversal controller out of slow Python hooks and into vLLM on the same GPU

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

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.

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.

AI safety content creator in Germany (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.

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

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.

safely.bio: Customer screening for DNA synthesis providers

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

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

Check Drexler's Estimates of Energy Dissipation in Nanosystems'

Persistent maybe conscious AI and whether it chooses for itself

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

Prediction of Inoculation Prompt Side Effects

An open, cheap method that detects when an inoculation prompt inoculates against off-target traits, so labs and developers can catch undesired trait/persona cha

FloraForge: Building a Reusable Genetic Platform for New Flower Traits