Database

Online platform where AIs and humans race to solve puzzles.

Building an AI research agent that can propose, test, and write up small ML findings

Deterministic, constant memory, continuous learning. Building the alternative to transformers

An incubator & community space in SF; for doers of good and masters of craft

A mechanistic, testable framework explaining LLM failure modes via boundary writes and attractor dynamics

No summary available yet.

Open-source replay tool and benchmark prototype for identifying step-level semantic risk transitions in multi-agent AI traces — CI-backed and independently repr

An open platform to stress-test how LLMs handle bias, pressure points, and clinical decisions. Built on peer reviewed real evidence.

Help turn the video from an amateur side-project to into an exceptional, animated distillation

An open-source framework for detecting and correcting agentic drift using formal metrics and internal control kernels

A contamination-free benchmark for measuring whether LLMs can forecast, or whether they're just remembering.

LLMs scale language, not method. HP turns hypothesis-driven papers into machine-readable maps of variables, controls, stats, and findings for researchers & AI.

Formalizing the "Safety Ceiling": An Agda-Verified Impossibility Theorem for AI Alignment

No summary available yet.

Programming language that enforces AI safety as runtime substrate properties rather than training-time alignment, already shipping on real hardware.

Free/Subsidized/Cheap office space outside of EU but in good timezones with favorable visa policies (especially for Chinese/Russian but also US&others near EU).

Let's warn millions of people about the near-term AI extinction threat by directly & proactively explaining the issue in every context where it belongs

Seeking short term grant to finance career transition

Novel safety failure modes discovered across 7 LLM providers with 35,000+ controlled inference trials. Targeting NeurIPS 2026.

$5,000 USD to bring 16 vetted academics and policy leads to NZ's first AI Safety Conference, ensuring national representation and cross-sector collaboration

Open Welfare Alignment Evals for Frontier Models

Building early AI governance and safety systems focused on alignment, oversight and risk reduction before more capable AI arrives.

Request for retroactive funding

A constraint-first approach to ensuring non-authoritative, fail-closed behavior in large language models under ambiguity and real-world pressure

Help Keep AI Safety ANZ Alive

No summary available yet.

A fast, comprehensive directory of the people and orgs in AI safety: search, filter, and match.

Incubate AI safety research and develop the next generation of global AI safety talent via research sprints and research fellowships

No summary available yet.

Assessing whether Persona drift be detected in conditionally misaligned models using the assistant axis and potentially analyzing the reasons for failure

Establishing a sovereign, decentralized Sentry node to audit frontier AI agents for logic escapes ($E_{escape}$) using the Inverted Social Drift ($SD$) metric.

Redefining AI's role in Human Connection and Interaction

Leveraging 12 Nobel signatories to harmonize lab safety thresholds and secure an international agreement during the 2026 diplomatic window.

No summary available yet.

Building a locally-run AI companion system designed to protect lonely and vulnerable users by tracking conversation shape, detecting distress, and making approp

Find the best settings for SAE training we can, then scale across models

Stipend to upskill under and collaborate with Sahil K and Topos for 4-6 months, seeking to obtain teleological DAGs as the dual of causal DAGs

Accepted ICML 2026 workshop paper on cross-constitution drift in LLMs; seeking $2,050 travel support to present in Seoul and gather research feedback.

Seeking funding to develop and evaluate a new benchmark for systematically assesing safety of LLM-based agents

A 10-case pilot using independent review and AI accountability to evaluate inscription claims

No summary available yet.

Making a simple, easy to read platorm, where alignment plans and their criticisms can be seen and ranked. Currently in Stage 1.

Software tools and research to quantify coordination failures and inform policy decisions.

Creating a cinematic AI safety documentary with entertainment value for the public. Need 5k to create trailer & foundational interviews.

The Reputation Circulation Standard - Implementation Sprint

Experimental message testing and historical analysis of tech movements to identify how to effectively mobilize people around AI safety and governance

No summary available yet.

4-month salary and initial expenses

My allocated travel funding is insufficient. Seeking extra funding for flights, accommodation, etc, to present poster and network