About the Program

The Human Frontier Collective (HFC) brings researchers and scientists together to tackle consequential problems in AI. In partnership with Scale Labs Preparedness and Policy (SLPreP), we are building a small cohort of researchers to work on the empirical foundations of AI safety.

The work includes thinking about various failure modes, evaluating whether safety controls hold up under pressure in realistic settings, and studying how AI agents (mis-)behave over long-horizon tasks. Residents take open research questions like these and turn them into work that improves how frontier AI systems are evaluated and safeguarded.

Research Areas

Mentors will guide AI safety residents on projects in AI safety research areas, such as:

AI control and chain-of-thought monitoring: Developing techniques to oversee and constrain AI systems, including monitoring their reasoning to detect harmful intent or deception.
Alignment red-teaming: Developing science around testing whether models have hidden goals, misaligned behaviors or unsafe tendencies.
Multi-agent safety: Studying the risks that emerge when multiple agents interact, such as collusion, coordinated failures, or unexpected collective behavior.
Recursive Self-Improvement (RSI) safety: Investigating how to keep AI systems safe and aligned as AIs increasingly contribute to their own development.
Science of Evaluations: Examining when and how models recognize they're being tested, and how situational awareness affects the reliability/validity of evaluations.
Misuse risks: Developing methods to assess how AI systems could be exploited by malicious actors, including evaluating their potential to enable harmful activities.

Projects are matched to demonstrated expertise; we don’t expect any candidate to cover every area.

Representative Research

ASPI: A benchmark with task–attack scenarios testing how clarification-seeking changes prompt-injection vulnerability in LLM agents.
PropensityBench: evaluating whether language models choose harmful actions when given simulated dangerous tools under various operational pressures
BioRiskEval: evaluating whether safeguards for open-weight bio-foundation models remain robust under fine-tuning and probing.
RSI Control: evaluating whether frontier models can covertly sabotage R&D efforts in the RSI loop.

See more work from the Human Frontier Collective.

What You'll Do

Projects are mentor-guided. Each resident will be given a list of research proposals and match you with one based on your research interests and background. You’ll meet weekly with a researcher from SLPreP who sets the direction and gives feedback, and you will drive the day-to-day work. By default, the project is expected to result in a conference paper.

Own research end to end: Turn a high-level safety question into hypotheses, baselines, and controlled experiments, and produce work that others can inspect and build on.
Build the measurement: Implement and debug evaluation harnesses, agent environments, datasets, monitoring methods, or post-training experiments.
Exercise research judgment: Identify confounds, separate what a model can do from what it tends to do, make sense of negative results, and decide what to try next without step-by-step direction.
Make the work legible: Produce reproducible code, experiment logs, analysis, and precise technical writing. External outputs, where appropriate, remain subject to research, security, and communications review. Outputs also include research papers, which will be submitted to top ML conferences (NeurIPS, ICML, ICLR).

Who We're Looking For

You may be a good fit if you:

are motivated by ensuring the safe and responsible development of advanced AI systems;
are interested in technical safety research, such as alignment evaluations, AI control, monitoring, multi-agent safety, or open-weight model safety;
are pursuing or have completed a PhD in CS, ML, statistics, mathematics, or a related field (we also encourage researchers with an equivalent track record to apply!);