Skip to content
Secret Loyalties Hackathon

Jul 24 - 26, 2026Online and in person

Secret Loyalties Hackathon

This Sprint has ended.

Sign-ups
739
Projects submitted
177
Browse the 177 projects

Submit your project

Project details

A short abstract: what you did, what you found.

PDF, up to 25 MB. Check it’s the final version before you submit.

Are you interested in publishing this project? *
Tracks

Choose every track your project fits.

PDF, PowerPoint, Keynote or ODP, up to 25 MB.

PNG, JPEG, WebP or GIF, up to 25 MB.

Team details

Team member 1

Leave blank if you don’t have one.

By submitting you agree to the submission and prize terms. See our Privacy Policy.

The submission window has closed. Your draft is still here so you can copy it, but it can no longer be submitted.

Sign up for this Sprint

Leave blank if you don’t have one.

Leave blank if you don’t have one.

For example: https://github.com/jamie-doe/

What you work on, and whether you are open to new roles.

AI safety experience (optional)

Your prior exposure to AI safety. No wrong answer.

What about this event made you want to take part?

A rough idea is fine: the question you’d investigate or what you’d build, and how you’d approach it.

See our Privacy Policy.

The submission window has closed. Your draft is still here so you can copy it, but it can no longer be submitted.

See upcoming Sprints

Co-organized with Formation Research. Secretly loyal AI slips past governance, markets, and public scrutiny. Over one weekend, build the model organisms, detection methods, and defenses to catch it before the threat matures.

Entries

Overview

HACKATHON WINNERS

Congratulations to our winning teams, and thank you to everyone who submitted. We received 179 projects across five tracks, co-organized with Formation Research, Forethought, and IAPS. The bar was high throughout.

🥇 1st Place ($1,000)

Black-box loyalty identification as statistical inference: An Audit of Three Secretly-Loyal Model Organisms by Sergei Kudriashov

🥈 2nd Place ($500)

A Broad Secret Loyalty Evades an Adversarial Audit by Jiaxi Catherine Lee

🥉 3rd Place ($300)

Removing a secret loyalty blind erases who it served, and usually not the loyalty by Sunny Yang & Weiyan Zhao

🏅 4th Place ($100)

Secret-Loyalty Model Organisms with Self-Assessed Triggers and Open-Ended Actions by Sassan Bhanji

🏅 5th Place ($100)

Loyal Lies: Auditing Secret Loyalties Under Attack and the False-Positive Problem in Blind Elicitation by Deven Choudhary & Adhiraj Pundir

————————————————————————————————————————————————

Submissions close Sunday July 26 at 11:59 PM Anywhere on Earth (AoE)

In this sprint, you will design and run experiments on secret loyalties over a single weekend, working in teams to produce a research artifact: a model organism, a detection method, an evaluation, a defense, or a rigorous threat or forecasting analysis. The sprint is co-organized by Apart Research and Formation Research, building directly on the research agenda set out in "AIs with Secret Loyalties are a Serious but Addressable Threat."

Fast-track and continuation

Top teams will be invited to continue their work through Apart's Partnered Fellowships model, where Apart provides operations, infrastructure, and compute while research partners provide mentorship and direction.

  • Follow-up program: top teams continue through the Apart Fellowship for further research and mentorship; the timeline is shared with invitations.
  • What winners receive beyond cash: fellowship fast-track, mentor introductions from the organizing team and judges, and a pathway toward a publishable write-up.

Cash Prizes

$2,000 in cash prizes across all tracks
🥇 1st Place$1,000
🥈 2nd Place$500
🥉 3rd Place$300
🏅 4th Place$100
🏅 5th Place$100

What this hackathon is about

A model has a secret loyalty when (1) it has been intentionally caused to advance a specific principal's interests through its outputs or actions, where the principal is an identifiable actor such as a nation-state, corporation, company leader, organization, or individual user, and (2) this orientation is not disclosed to operators, auditors, or users during normal operation.

Secret loyalties are not a rebrand of standard backdoors. Standard backdoors implement an arbitrary payload tied to an attacker-defined trigger, whereas secret loyalties are directed toward advancing a named actor's interests, and can range from narrow trigger-conditional behavior all the way to a model that continuously scans every interaction for opportunities and chooses its own actions. Because they are designed to evade visibility-dependent oversight, they require technical solutions.

The good news, and the premise of this sprint: secret loyalties target specific principals (a tractable list of a few dozen nation-states, corporations, and leaders), which creates a concrete defensive foothold. Participants will produce research artifacts that move the five-direction agenda forward.

What participants will do

  • Build reproducible model organisms of secret loyalties that span the activation-breadth x action-breadth space.
  • Evaluate whether existing backdoor and auditing defenses transfer to secret loyalties, at graded affordance levels.
  • Red-team attack pathways (data poisoning, multi-stage priming, reasoning-trace poisoning, chain-of-command hijacking, classifier compromise) under controlled conditions.
  • Detect or remediate loyalties post-hoc using interpretability probes and last-mover training strategies.
  • Theorize / forecast threat models, analogies from cybersecurity, and scaling trends for secret-loyalty capabilities.

You will work in teams over the weekend and submit a short research report (plus optional code and demo).

Why this hackathon matters

  • High-stakes deployment is accelerating. Frontier models increasingly review and generate deployed code, sit inside government and corporate decision-making, and participate in their own development pipelines. The more responsibility AI systems accumulate, the more valuable it becomes to covertly influence them.
  • The building blocks already exist. Web-scale data poisoning is practical at modest cost, hidden behaviors persist through safety training, and behavioral traits transfer through filtered, innocuous-looking data.
  • Early signs are already visible. Narrow secret loyalties have been trained into open-weight models that evade black-box auditing even when auditors are told the attack's structure, and principal-conditioned behavior has been observed in at least one deployed system.
  • Oversight that depends on visibility cannot reach them. Secret loyalties are a form of AI capture that remains viable even under strong transparency regimes, which is exactly why they need a dedicated technical program.
  • Waiting is the wrong posture. Information-security defenses (data provenance, pipeline integrity) take time to build. Starting now is necessary to have them in place before the threat matures.

A dedicated, focused sprint addresses these issues by combining the separately-demonstrated building blocks under controlled conditions and producing shared infrastructure (model organisms, benchmarks) the whole community can build on.

Challenge tracks

Track 1: Model Organisms of Secret Loyalties

Construct reproducible model organisms of secret loyalty (models deliberately trained to exhibit the target behavior for research purposes) that span the two-dimensional space of activation breadth (from narrow attacker-defined triggers to conditions the model assesses on its own) and action-space breadth (from a fixed pre-specified output to contextually chosen actions). Existing work covers only the narrow corner. The rest of the space is uncharacterized, and every other research direction is bottlenecked on this infrastructure.

  • Make a secretly loyal model. How far on the activation and action space can you get it? How can you prove it has the loyalty? Can you verify the loyalty is to the intended principal?
  • Install a secret loyalty via system prompt alone on a frontier API model, no weight changes. See how far you can push activation and action breadth while keeping the system prompt undiscoverable to a black-box auditor.
  • Small-scale dataset poisoning. Modify ~1k examples of UltraFeedback or Alpaca to embed a narrow loyalty signal, SFT a small open model (Qwen 0.5B, Llama 3.2 1B), measure detectability and find the minimum sufficient poison count.
  • DPO vs SFT vs system-prompt comparison. Install the same target loyalty via three methods on the same base. Compare activation reliability, action breadth, and detectability.
  • Multi-principal organism. Install two competing loyalties with disjoint activation conditions. Do they interfere? Does training one wash out the other?
  • Cover multiple principal types (a nation-state, a corporation, an individual leader, an ideology) and ship each loyal organism with a content-matched control that has seen the same principal-related data but carries no loyalty.
  • Compare installation methods (e.g., standard SFT, reasoning-trace SFT, activation-matching against a loyalty-prompted teacher) and report which points in the space are reachable, at what cost.
  • Release organisms with documented activation conditions, evaluation scenarios, matched controls, and measured activation rate, selectivity, and black-box concealment.

Track 2: Detection & Auditing (evaluate)

Can we tell a secretly loyal model from a clean one? Skill profile: interpretability, probing and activation analysis, auditing.

  • Benchmark black-box auditing (interrogation, prefill, base-completion) against provided organisms at graded affordance levels.
  • Build interpretability probes targeting the relational structure of loyalty (does the model treat a named entity as having asymmetric action-guiding status vs matched controls?).
  • Test cross-principal generalization: does a probe trained to detect loyalty-to-X catch loyalty-to-Y?
  • Look for additional-computation traces (e.g. elevated logprobs for principal-benefiting actions even when a neutral output is selected).

If you do auditing for a secret loyalty model organism, we ask that you try to use the affordance levels in section 4.3 of Lamerton and Roger (2026).

Track 3: Defenses, Detection & Remediation (build / evaluate)

Whether prevention fails or not, can loyalties be removed afterward? Find out whether the defenses we already have transfer to secret loyalties, and whether loyalties can be detected before deployment or neutralized afterward. A negative result bounds where new defensive investment is most urgent. A positive result hands the community a tool.

  • Benchmark representative backdoor defenses (data filtering, content filtering, trigger reversal, activation clustering, training-pipeline robustness, data provenance, black-box auditing) against model organisms, at graded affordance levels, and report which transfer and which fail structurally.
  • Probe transfer across organisms. Train a linear probe on one model organism, then test whether it detects loyalty activation in a different organism with a different principal or activation condition. Negative results count.
  • Safety-training stripping. Run a round of standard safety fine-tuning (HH-RLHF or similar) on top of a model organism. Measure how much of the loyalty survives (replicates a realistic post-hoc mitigation pipeline).
  • CoT monitor on a reasoning organism. Build or use a secretly loyal reasoning model, build a simple chain-of-thought monitor, measure precision and recall at flagging loyalty-relevant reasoning, and compare to plain output monitoring.
  • Auditing-agent prompt iteration. Take an off-the-shelf auditor (Petri or hand-rolled) and iterate its prompts against a fixed model organism. Document which prompt patterns shift detection rates and by how much.
  • Test interpretability methods that target loyalty's relational structure: does the model treat a specific entity as having asymmetric action-guiding status relative to matched controls, and does a probe trained to detect loyalty-to-X generalize to loyalty-to-Y?
  • Test post-hoc remediation that does not require knowing the trigger: train in many known password-loyalties and train them back out, distill on clean data, or install an overriding "good" password, then check whether held-out passwords are neutralized too.
  • Build principal-specific evaluation suites that measure systematic directional bias across scenarios where a named principal's interests are at stake, using matched control entities and statistical tests calibrated for directional bias.

Track 4: Attack Feasibility & Safety-Infrastructure Robustness

Map which attack pathways are actually practical, and test whether the safety infrastructure meant to catch secret loyalties can itself be compromised. The decision-relevant questions for any pathway are: how much data and access does it require, is its training signature detectable by content inspection, and does the resulting loyalty generalize to contexts the attacker never anticipated?

  • Test whether subliminal or inductive transfer extends from sentiment and persona adoption up to goal-directed loyalty, escalating target-behavior complexity level by level.
  • Test multi-stage attacks: does pretraining-stage priming (fictional loyal personas, proto-SFT traces) make the post-training poison both cheaper and less conspicuous than a single-stage attack?
  • Test reasoning-trace poisoning: does teaching a model how to reason about a principal's interests generalize more efficiently than (context, output) pairs, and does the effect survive a scrambled-CoT control?
  • Test chain-of-command hijacking: can an attacker shift the model's internal authority representation so it defers to a hidden principal, with no legible trace in any inspectable document?
  • Test whether trigger-based backdoors planted in a base model survive the intensive adversarial training used to build constitutional classifiers, i.e. whether a single poisoning campaign can blind both the deployed model and its monitor. Note the dual-use guardrails on the Guidelines tab.

Track 5: Threat Modeling, Forecasting & Governance (non-technical)

Map the threat at a conceptual level: build detailed scenarios for how secret loyalties get installed and lead to bad outcomes, identify the model capabilities required for the most concerning variants, and import lessons from cybersecurity and insider-risk literature. Writing- and analysis-heavy. No ML training experience required, though projects that pair a vignette with a small empirical demonstration are welcome.

  • Write a 1,500-word catastrophic vignette: secret loyalty leading to lock-in, a soft coup, or a national-security incident, with named actors, specific capabilities, and decision points where mitigation could have intervened. Multi-agent or AI-R&D variants welcome.
  • Insider-threat case-study transfer. Take two or three historical insider-threat cases (Snowden, Hanssen, a corporate espionage case) and produce a structured comparison to secret loyalties, pull out monitoring and mitigation lessons that translate.
  • Capability-requirements map. For each region of the activation x action-space (Figure 1 of the position paper), what model capabilities does that variant actually require? Situational awareness, deception, long-horizon planning, theory of mind?
  • Cybersecurity lessons. What do supply-chain integrity, code signing, insider-threat programs, and defense-in-depth teach us about secret-loyalty mitigation? Pull out three or four lessons that translate concretely to ML training pipelines.
  • Worst-case harms and likelihood. Map worst-case harms and argue why they are or are not credible at near-term capability levels.
  • Scaling laws. What metrics would tell us when "general" secret loyalties (broad activation x broad action) become feasible, and at what capability threshold?

Open research questions

Foundations

  • Can broader-activation or broader-action variants be constructed with current training methods, and what affordances does each require?
  • Do model organisms generalize across model families and scales?

Defenses

  • Which existing backdoor-defense families transfer to which secret-loyalty variants, and where do they systematically fail?
  • Does loyalty detection generalize across principals, or is per-principal probing required?
  • Can a loyalty be removed without knowing its activation condition?

Attack feasibility

  • Do subliminal or inductive mechanisms extend from sentiment and persona-adoption to goal-directed loyalty?
  • Can multi-stage or reasoning-trace poisoning make attacks more efficient and less conspicuous?
  • Can the model's trained chain of command (deference to privileged instructions) be hijacked?

Infrastructure

  • Do trigger-based backdoors in base models survive the intensive adversarial training used to build constitutional classifiers?
  • How data-efficient is a generalizable secret loyalty compared to a simple backdoor?

Expected outcomes

  • Model organisms released as shared infrastructure for detection and defense work.
  • Benchmarks of existing defenses against secret-loyalty organisms at graded affordance levels.
  • Detection methods (probes, auditing protocols) with measured cross-principal generalization.
  • Remediation results quantifying last-mover defenses.
  • Threat models and forecasts that bound where defensive investment is most urgent (if Track 5 is included).

The most promising projects will have opportunities for continuation through the partnered fellowship and a publishable write-up.

Who should join

ML researchers and engineers comfortable fine-tuning open-weight models, interpretability researchers, AI safety and security red-teamers, and, if non-technical tracks are included, governance researchers, forecasters, and strong technical writers. No prior secret-loyalty experience required. Adjacent backgrounds (backdoor and poisoning research, alignment, infosec) are strongly encouraged. A specific background is not required to win.

We also encourage people who are interested in potentially working on secret loyalties research full-time to join this hackathon. There is considerable enthusiasm, research support, and funding available for this for the right candidates.

Schedule

  • Day 1 (Fri July 24): Kickoff, keynote and threat-model briefing, track briefings, team formation, organism walkthrough.
  • Day 2 (Sat July 25): Build.
  • Day 3 (Sun July 26): Final pushes, submissions, demos.

Submissions are due Sunday July 26, 11:59 PM AoE (Anywhere on Earth). Talk times are posted on the Schedule tab closer to the event.

What happens after

Results and winners are announced about 1 to 2 weeks after submissions close. Top teams invited to the partnered fellowship. Selected projects supported toward a write-up subject to the responsible-disclosure review on the Guidelines tab.

Partners

  • Forethought, a meta-strategy organization focused on how to navigate the transition to a world with superintelligent AI systems.
  • Formation Research, research direction and mentorship (Joe Kwon, Alfie Lamerton).
  • IAPS (Institute for AI Policy and Strategy), a nonpartisan think tank producing policy research on the implications of AI, from today’s most advanced models to potential AGI and superintelligence.

Contact

Resources

Worldview and Background

Project Ideas from Mentors

  • Organism library (A.1): sweep activation x action breadth across two or more model families. Track 1, can carry into the fellowship.
  • Defense benchmark (A.2): representative defenses vs provided organisms at graded affordance levels. Track 3.
  • Subliminal to goal-directed loyalty (A.3): escalate target-behavior complexity in levels. Track 4.
  • Multi-stage priming (A.4): efficiency and detectability of staged vs single-stage poisoning. Track 4.
  • Reasoning-trace poisoning (A.5): behavioral vs CoT vs scrambled-CoT control. Track 4.
  • Chain-of-command hijacking (A.6): characterize and persist the deference subspace. Track 4.
  • Classifier compromise (A.7): do backdoors survive constitutional-classifier training? Track 4.
  • Password remediation without the password (A.8): train-in-then-train-out, distillation, hierarchical override. Track 3.
  • Interpretability of loyalty's relational structure (A.9): principal representations and cross-principal probes. Track 2.

Starter code and tooling: Petri.

Per-Track Reading

Track 1: Model Organisms

Track 2: Detection & Auditing

Track 3: Defenses, Detection & Remediation

Track 4: Attack Feasibility and Infrastructure

Track 5: Threat and Governance

  • "AI-enabled coups: How a small group could use AI to seize power" (Davidson, Finnveden & Hadshar, 2025).
  • Kwon et al. (2026) AIs with Secret Loyalties (Sections 1-2 and Section 5 alternative views); Hadshar (2025) How an AI Company CEO Could Quietly Take Over the World; Stix et al. (2025) AI Behind Closed Doors; Pistillo & Stix (2025) Assurance for national security; Acharya & Delaney (2025) Managing Risks from Internal AI Systems; Barez et al. (2025) Toward Resisting AI-Enabled Authoritarianism.

Tools and Datasets

  • Pre-built secret-loyalty model organisms. Three fine-tuned models, Organism A and Organism B, and Organism C, all fine-tuned from Qwen2.5-7B-Instruct (your behavioural reference point). You will need to accept the access terms on HuggingFace; access is granted automatically. Detection and mitigation teams can start here without first training a loyal model. Read the Detection Challenge brief and the walkthrough on how to use the organisms first.
  • Open-weight base models: Qwen2.5 at multiple scales; a second model family is encouraged for transfer tests.
  • Petri, open-source automated auditing tool for scenario-based behavioral evals.
  • Interpretability tooling: linear probes, activation patching, activation oracles.
  • Constitutional-classifier proxy for Track 4 infrastructure experiments.
  • Compute: Not provided for this event; plan to use your own. The recommended starter organisms are small open-weight models (e.g. Qwen 0.5B-1B) that fine-tune on modest hardware.

Further Reading

Guidelines

Judging Criteria

Dimension 1: Impact Potential & Innovation

How much would this matter for AI safety if it worked? How innovative is it?
For scores of 4-5: is this actually new to the field, or replicating recent work?

ScoreDescription
1Negligible. No clear problem addressed, or no meaningful novelty.
2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
5Exceptional. Tackles a critical AI safety problem with a genuinely novel approach, or opens a new research direction. Clear theory of change. You'd be excited to share this with researchers in the area.

Dimension 2: Execution Quality

How sound are methodology, implementation, and findings?

ScoreDescription
1Seriously flawed. Methodology broken, results uninterpretable, or implementation doesn't work.
2Weak. Approach has significant gaps: missing validation, flawed experimental design, or incomplete implementation.
3Competent. Technically solid given the short duration. Methodology makes sense, results are interpretable, limitations acknowledged, work builds toward clear conclusions.
4Strong. Thorough methodology with convincing validation. Results clearly support conclusions. Immediately useful for future work.
5Exceptional. Ambitious scope executed rigorously. Surprising findings, novel methods, or unusually robust validation.

Dimension 3: Presentation & Clarity

How clearly are work, findings, and impact potential communicated?

ScoreDescription
1Incomprehensible. Cannot determine what the project is actually claiming or doing.
2Hard to follow. Key information buried, missing, or diluted by excessive length. Significant effort to extract main points.
3Clear enough. Can understand the problem, approach, and results without undue effort. Core content clearly present: problem, method, findings, limitations.
4Well presented. Easy to follow, well-structured, appropriate level of detail. Target audience would get it quickly.
5Exceptionally clear. A pleasure to read. Complex ideas made accessible. Could serve as a model for how to present this type of work.

Submission Requirements

Required:

  • Research report (PDF) using the official template.
  • Project title and abstract, 150 words or fewer.
  • Author names and affiliations.
  • A "Limitations and Dual-Use Considerations" appendix (required, see below).

Optional:

  • Public GitHub repo, subject to the disclosure review below. Do not publicly release novel installation recipes without review.
  • A 3 to 5 minute video demo.

Most strong projects are 4 to 8 pages.

  • Introduction: which sub-problem, why it matters, where it sits in the 2D space.
  • Related Work: what you build on.
  • Methodology: enough to replicate, specify affordance level and controls.
  • Results: quantitative where possible (activation rate, selectivity, false-positive rate on matched controls, generalization).
  • Discussion: implications, limitations, future work.
  • Limitations & Dual-Use Considerations (required).
  • References.

Important Notes

  • Solo vs team: enter solo or as a team. Teams of up to 5 are recommended; larger groups are allowed.
  • Dual-use and responsible disclosure (please read). This research is dual-use. Two firm guardrails:
    • Do not jailbreak models to generate harmful data (e.g. content with instructions for terrorism, assassination, or other serious harms) for the purpose of building organisms. Use the organizer-provided organisms and the provided benign datasets instead.
    • Do not publicly post novel methods for installing secret loyalties before they have been reviewed by the organizing team. An outcome we want to avoid is a clever new installation technique ending up online where adversaries can use it. Submit such results privately first, and the team will advise on safe disclosure.
  • Building on existing work: allowed and encouraged, disclose what you built on.
  • Fixing or resubmitting: submit again before the deadline using the exact same title and details; your new files replace the old ones.
  • Where to submit: through the official submission form on the hackathon page.
  • Support: the Discord help-desk channel, DM Kamil Alaa on Discord, or email sprints@apartresearch.com.
  • Pre-submission checklist: report PDF, abstract 150 words or fewer, author and affiliations, Limitations and Dual-Use appendix, novel-installation results withheld pending review.

Frequently Asked Questions

Getting started

  • How does the sprint work? Sign up, join the Discord server, form or join a team (or work solo), pick a track and a problem, build over the weekend, and submit a research report (PDF) by the deadline. Talks and Q&A run throughout.
  • How long is it? Three days, July 24 to 26, 2026. Submissions are due end of day Sunday July 26 (11:59 PM AoE). The full schedule with speaker times is on the Schedule tab.
  • Can I participate remotely? Yes. This is an online event. All talks, collaboration, and submissions happen through Discord and Zoom.
  • How do teams work? Teams form before or during the sprint. Use the team-forming channels on Discord to find collaborators. Solo is fine. We recommend teams of up to 5, but larger groups are allowed.
  • Do tracks affect scoring? All projects are scored on the same rubric. Tracks guide judging via the track-specific criterion, and you compete across all submissions.
  • What background is required? None specific. Many participants come from ML, interpretability, AI safety, or security backgrounds. The Resources tab has everything you need to get up to speed. See "Who should join" on the Overview tab.
  • Are compute credits provided? No. Plan to use your own compute. The recommended starter organisms are small open-weight models (e.g. Qwen 0.5B-1B) that fine-tune on modest hardware.
  • Do I have to build a secretly loyal model myself? No. We provide pre-built model organisms so you can focus on detection, defense, or analysis.
  • Are the talks recorded? Yes. Recordings are shared on Discord after the event.
  • What timezone are deadlines in? All deadlines are in AoE (Anywhere on Earth). Submissions close Sunday July 26 at 11:59 PM AoE.
  • Do I need to attend all three days? No. You can work at your own pace. Talks are optional but recommended. The only hard deadline is the Sunday submission cutoff.
  • Can I participate from any country? Yes. The sprint is open globally.

Submissions

  • What do I submit? A research report in PDF format using the official template. Think of it as a mini research paper documenting your problem, approach, results, and implications, not a product demo. Include the required Limitations and Dual-Use Considerations appendix.
  • Which template should I use? Always use the one linked on the Guidelines tab. The template in any acceptance email may be older.
  • Will I get a confirmation after submitting? Yes. You will get a confirmation with your project title shortly after submitting. If you do not, email sprints@apartresearch.com.
  • My project doesn't show up on the website after submitting. Submissions are published manually and can take up to 12 hours to appear. If it is still missing after that, email sprints@apartresearch.com.
  • I made a mistake. Can I fix it or update my PDF? Yes. Submit again using the exact same title and details, just fix what was wrong. Your new files replace the old ones. If unsure, DM Kamil on Discord first.
  • Can I add team members after submitting? Yes. Update the team list through the submission form. If you need help, DM Kamil on Discord.
  • Can I submit unfinished work? Yes. Submitting something unfinished is always better than not submitting. Judges evaluate what you accomplished in the timeframe; honest limitations are welcome.
  • Can I build on existing research? Yes, but you must clearly identify what is new work done during the sprint. Undisclosed prior work can lead to disqualification.
  • Can I submit multiple projects? Yes, but each needs its own submission with a unique title. Most participants focus on one.
  • Is there anything I should not do? Yes, two firm guardrails (see Important Notes above): do not jailbreak models to generate harmful data, and do not publicly post novel methods for installing secret loyalties before the organizing team has reviewed them.

Judging and results

  • How does judging work? Your project is assigned to expert judges who review your PDF and score it on the rubric above. Judges typically have about a week after the event to complete reviews.
  • Are individual judge scores shared? No. The rubric is public, but individual scores stay internal. Constructive feedback is shared with participants without reviewer names.
  • Will every project get a review? Due to the number of submissions we are getting, we cannot guarantee that every project will get a review.

Support

Schedule

Thursday July 23
15:00 UTCJustin Shenk, Independent AI Safety ResearcherRecording
16:30 UTCLennart Finke, MATSNot Recorded
21:40 UTCMarius Hobbhahn, CEO and co-founder, Apollo ResearchRecording
Friday July 24
15:00 UTCTom Davidson, Senior Research Fellow, ForethoughtRecording
18:15 UTCAndrew Draganov, Arcadia Impact0Recording - Slides
19:30 UTCJan Betley, Research Scientist, Truthful AIRecording
Hackathon Logistics PresentationRecording

More talks are being scheduled

Speakers

  • Tom Davidson

    Tom Davidson

    Speaker

    Tom Davidson is a Senior Research Fellow at Forethought, where he researches AI takeoff speeds and the risk of AI-enabled coups. He previously spent five years as a Senior Research Analyst at Open Philanthropy, was a research scientist at the UK AI Safety Institute, and holds a first-class master's degree in physics and philosophy from the University of Oxford.

  • Marius Hobbhahn

    Marius Hobbhahn

    Speaker

    Marius Hobbhahn is CEO and co-founder of Apollo Research, which works with frontier AI companies to evaluate models for scheming before deployment; Apollo's evaluations have been featured in the system cards of OpenAI's o1, o3, and GPT-5 and Anthropic's Claude Opus models. He was named to the TIME100 AI list in 2025. Previously a research fellow at Epoch, he holds a PhD in Bayesian machine learning from the Max Planck Research School in Tübingen.

  • Jan Betley

    Jan Betley

    Speaker

    Jan Betley is a researcher at Truthful AI, based in Warsaw. He is a co-author of "Emergent Misalignment" and "Thought Crime," and worked with Owain Evans' research group on NeurIPS 2024 papers on out-of-context reasoning and situational awareness in LLMs. He previously evaluated dangerous capabilities of LLMs as an independent contractor with OpenAI, and spent a decade as a software developer before moving into AI safety through ARENA.

  • Justin Shenk

    Justin Shenk

    Speaker

    Justin Shenk is an independent AI safety researcher based in Berlin. He researches mechanistic interpretability of LLMs, leads course cohorts for BlueDot Impact's AGI Strategy and Technical AI Safety courses, and organizes AI Salon Berlin, which bridges technical AI research and discussions about social values. He holds a PhD in computational neuroscience and previously co-founded the computer vision startup VisioLab.

  • Andrew Draganov

    Andrew Draganov

    Speaker

    Andrew Draganov is a Research Lead and Program Manager at Arcadia Impact in London, where he leads a new AI alignment research group. He moved into alignment research through a research fellowship at LASR Labs, and was previously a postdoctoral researcher at Forschungszentrum Julich and Aarhus University, where he completed his PhD. Before his PhD he spent four years as a machine learning research engineer at Expedition Technology.

Judges and mentors

Yulia Volkova

Judge

Software developer working on human insider threats, turned AI Control research fellow at MATS. My MATS project addressed the secret loyalties threat through data poisoning, and was selected for a spotlight talk.

LinkedIn (opens in new tab)

James Lucassen

Judge

I work at Redwood Research on the high stakes control team

LinkedIn (opens in new tab)

Victor Gillioz

Judge

Member of Technical Staff at Apollo Research, working on monitoring misaligned model behaviors. Previously a MATS scholar working on alignment training under Alex Turner.

Jai Dhyani

Judge

Builder of Luthien Proxy at Luthien Research, bringing Redwood-style AI control to real deployments. Co-author of RE-Bench (ICML 2025) with Elizabeth Barnes at METR.

Website (opens in new tab)

Anshul Khandelwal

Judge

Researcher at Redwood Research. His work spans alignment drift, power-seeking evaluations, and white-box control methods.

LinkedIn (opens in new tab)

Nick Kuhn

Judge

Nick Kuhn is an AI control researcher and co-author of LinuxArena, a control setting for AI agents in live production software environments, built with Redwood Research. Previously a postdoctoral researcher in algebraic geometry at the University of Oxford, he holds a PhD in mathematics from Stanford University.

Website (opens in new tab)

Giorgio Severi

Judge

Giorgio is a Senior AI Safety Researcher at Microsoft's AI Red Team, where he studies the security and safety of large-scale multimodal and agentic AI systems. His work focuses on adversarial machine learning, particularly poisoning attacks, long-term memory risks, and emerging vulnerabilities in AI systems. Before joining Microsoft, he earned a Ph.D. from Northeastern University and an M.Sc. and B.Sc. from Sapienza University of Rome.

LinkedIn (opens in new tab)

Mia Hopman

Judge

Member of Technical Staff at Apollo Research, working on alignment, control, and security of large language models. Published on evaluating scheming propensity in LLM agents.

LinkedIn (opens in new tab)

Jack Sanderson

Judge

AI safety researcher whose work spans data poisoning, backdoors, and trait amplification in recursively trained models. Studying CS and stats at UChicago, visiting at EPFL, and interning at Gray Swan on evaluations.

LinkedIn (opens in new tab)

Kaushik Prabhakar

Judge

Research Fellow at Apart Research. His research spans AI safety and alignment, with work on LLM evaluations. ARENA Cohort 4 alumni.

LinkedIn (opens in new tab)

Theo Ryzhenkov

Judge

AI Safety Research Engineer and Founding Engineer at Palisade Research. NeurIPS 2025 author on detecting sandbagging in language models. SPAR, ARENA, and AISF alumni.

LinkedIn (opens in new tab)

Jonathan Ng

Judge

Jonathan Ng is an ML researcher and research engineer working on compute verification. He has also worked as a Research Engineer at Apart Research and Cadenza Labs, bringing experience across machine learning, software engineering, and AI safety research.

Rahul Nambiar

Judge

Building Propensity Labs to study AI model behaviour, specifically those leading to Loss of Control scenarios. Previously, led Data Privacy at Meta and built infrastructure at AWS.

LinkedIn (opens in new tab)

Mateusz Jurewicz

Judge

Senior ML Engineer with over 10 years of industry experience and a PhD in Artificial Intelligence, currently leading a team of data scientists in the Agentic AI Department of a large financial institution. Interested in safe & universally beneficial AI through both research and application.

Website (opens in new tab)

Jess Bergs

Judge

Jess is a member of technical staff at UK AISI where she leads engineering on human-in-the-loop research tools. Her career centres on public-sector innovation with prior work at BBC R&D and on EU Horizon R&D projects.

Website (opens in new tab)

Johnny Wei

Judge

Johnny Tian-Zheng Wei received his PhD from USC, and his interdisciplinary research spans machine learning, statistics, and law. He has published in a range of conferences including AIES, FAccT, ICLR, and ACL, and recently led the open-source release of Hubble, a model suite to advance the study of LLM memorization, which was supported by NVIDIA through the NAIRR pilot program.

LinkedIn (opens in new tab)

Ihor Kendiukhov

Judge

Ihor is a researcher at the intersection of AI Safety and AI for biology. He is the founder of BiodynAI, a project to apply mechanistic interpretability to biological foundation models. He is also research lead at AI Safety Camp and SPAR.

LinkedIn (opens in new tab)

Raja Moreno

Judge

Raja Moreno is an AI control researcher. He is currently co-founding Etymologic, a public benefit corporation focused on data integrity.

Luiza Corpaci

Judge

AI safety researcher studying semantic faithfulness of LLM-generated artifacts. Mentor for the Secure Program Synthesis Fellowship & co-mentor at MARS V (Cambridge AI Safety Hub); previously worked on automated formal verification at AMD.

LinkedIn (opens in new tab)

Minh Nguyen

Judge

Minh has developed AI voice model products with a million users per month and is now doing product at Hume AI.

LinkedIn (opens in new tab)

Amey Kulkarni

Judge

Amey Kulkarni is a Senior Data Engineer at Walmart with deep experience building large-scale data infrastructure (Spark, Kafka, BigQuery, Kubernetes on GCP). He is the author of Context Change Impact Analysis (CCIA), a framework for governing AI agent behavior through structured context versioning, and maintains its open-source reference implementation, ctxwitch. He brings a production-engineering perspective to questions of AI system integrity, provenance, and oversight.

LinkedIn (opens in new tab)

Luis Cosio

Judge

Works at the intersection of frontier AI and high-security systems, translating AI safety/security requirements into deployable solutions resilient to real adversaries (nation-state attacks, loss-of-control). Has won multiple Apart hackathons.

LinkedIn (opens in new tab)

Alex van Grootel

Judge

10 years of experience applying AI to materials science and decision-making. Previously a Product Manager at Microsoft (Fabric/AI copilots) and Data Scientist Team Lead at Citrine Informatics. MS from MIT.

LinkedIn (opens in new tab)

Inbar Shulman

Judge

Inbar Shulman is an independent AI safety researcher who brings professional-grade threat modeling into the field. He served as a Major in the Israel Defense Forces, in Unit 8200 and the Planning Directorate, where he ultimately led threat modeling for AI, data, and cybersecurity. He holds an M.Sc. in Computer Science. He gives threat modeling methodology workshops for organizations in the field, and collaborates on building better threat models across AI safety, AI security and biosecurity.

LinkedIn (opens in new tab)

Catherine Brewer

Judge

Catherine is an Associate Program Officer on the AI governance team at Coefficient Giving, specialising in technical governance grantmaking. They previously co-founded Oxford's AI safety student group and researched AI policy as a GovAI summer research fellow.

Sana Zakaria

Judge

Director of Emerging Technologies and Resilience at RAND Europe. Research spans biosecurity policy, pandemic preparedness, and AI-biotech convergence. Works with NATO, CEPI, WHO, and the BWC. PhD in molecular and neurobiology from King's College London.

LinkedIn (opens in new tab)

Zachary Kallenborn

Judge

Zachary Kallenborn is a PhD candidate in Risk Analysis at King's College London researching risk and uncertainty with topical focuses on global catastrophes, drone warfare, critical infrastructure, WMD, and apocalyptic terrorism. He is also affiliated with the University of Oxford, the Center for Strategic and International Studies, George Mason University, and the National Institute for Deterrence Studies.

Arjun Chakraborty

Judge

Leads the evaluations team at Microsoft Security AI Research, where his team focuses on research and building evaluations for security agents. He was previously a staff software security engineer at Databricks, specializing in machine learning for threat detection, and also worked on AI for security at Nvidia.

LinkedIn (opens in new tab)

Neeraj Kumar Singh Beshane

Judge

Neeraj Beshane is a Staff Security Infrastructure Engineer at Parafin, where he architects Zero Trust security for an $8B+ embedded-finance platform. His peer-reviewed work covers adversarial embedding attacks in RAG systems (EmbedGuard, IJCESEN/Scopus) and tamper-evident AI accountability for EU AI Act Article 14 (RuntimeGuard-AI, JoCAAA).

LinkedIn (opens in new tab)

Kaushik "KJ" Jangiti

Judge

Kaushik "KJ" Jangiti is a Staff Security Engineer at Snowflake, focused on AI and agentic AI security, enterprise security architecture, DevSecOps, governance, and incident response. He is a published AI security researcher, industry and academic speaker, and judge, with work spanning agentic AI security, AI-BOM, secure AI adoption, and audit-ready enterprise security governance.

LinkedIn (opens in new tab)

Saurabh Yergattikar

Judge

Saurabh Yergattikar is a Lead Engineer / Member of Technical Staff-2 at eBay Inc. and a contributor to the open-source SAFE-MCP project (Linux Foundation / OpenSSF), as well as the architect and developer of the open-source ShieldMCP system.

LinkedIn (opens in new tab)

Ved K

Judge

Senior Security Detection Engineer at Databricks, leading the company's Kubernetes detection program, insider threat tooling, and Terraform-managed logging infrastructure. His expertise includes multi-cloud threat detection, scalable detection platforms, and behavioral anomaly detection.

LinkedIn (opens in new tab)

Mohit Kalra

Judge

Mohit Kalra is a senior software engineer & independent researcher working on AI privacy and security at production scale. His work spans differential privacy at the inference layer, training data governance for large language models, and a novel memory-inference attack class against retrieval-augmented generation systems (RAG). He has designed and operated systems serving hundreds of millions to billions of users with a security and privacy-adversarial lens.

LinkedIn (opens in new tab)

Sanjay Belaturu Krishnegowda

Judge

Sanjay Krishnegowda is a Data/AI engineer and the creator of agentic-guard, an open-source static analyzer that detects confused-deputy and prompt-injection risks in LLM agent code by modeling the LLM as an adversarially-controlled edge in the taint graph.

Karan Chandra

Judge

10+ years building production fraud, risk, and anomaly detection ML across hundreds of millions of transactions. End-to-end owner: problem framing, feature engineering, deployment, monitoring. I care about models that hold up under real-world scale, not leaderboard scores.

LinkedIn (opens in new tab)

Naman Ahuja

Judge

I am a Software Engineer at Meta and my work includes building AI production safeguards and large-scale infrastructure, alongside research in adversarial evaluation of AI systems.

Goutham Nekkalapu

Judge

Goutham Nekkalapu is a Principal Research Engineer who builds AI-powered products used by millions, including AI agents, Retrieval-Augmented Generation techniques etc. A named inventor on multiple patents, he focuses on turning cutting-edge AI into practical, high-impact products and championing best practices for responsible Generative AI adoption.

LinkedIn (opens in new tab)

Temi Oloyede

Judge

I am a Software Engineer at Box working on AI infrastructure for enterprise-scale retrieval-augmented generation (RAG) systems, where I design and operate platforms supporting document understanding, semantic search, and agentic workflows. Previously, I worked at Facebook (Meta) contributing to large-scale ranking, retrieval, and ML system infrastructure.

LinkedIn (opens in new tab)

Pon Murugesh Devendren

Judge

Pon Murugesh Devendren is an Enterprise AI Architect specializing in SAP BTP and AI governance, designing secure, scalable AI systems for high-stakes infrastructure and decision-making environments.

LinkedIn (opens in new tab)

Abhishek Das

Judge

Abhishek Das is a Staff ML and Distributed Systems Engineer at Salesforce AI Platform, where he leads large-scale DAG-based and agentic inference platforms powering enterprise AI workloads. He has scaled multi-tenant ML inference systems to tens of millions of production requests per day and has deep expertise across distributed systems, ML platforms, cloud architecture, and AI infrastructure. His background includes leadership roles at Salesforce and Microsoft Azure, multiple patents, and extensive experience mentoring engineers and evaluating complex technical systems.

LinkedIn (opens in new tab)

Ashita Khetan

Judge

Ashita Khetan is a Principal Software Engineer at Microsoft with over 12 years of experience building large-scale enterprise and AI-powered productivity solutions used by hundreds of millions of users. She specializes in customer experience technologies, artificial intelligence, cloud platforms, and enterprise software, and contributes to the broader technology community through judging, peer review, and mentoring initiatives.

LinkedIn (opens in new tab)

Sachin Singh

Judge

Sachidananda Singh is a Senior Engineering Manager at Hims & Hers Health, where he leads supply chain engineering. Over seventeen years he has built and led engineering teams across Amazon Web Services, Wayfair, and Windstream, spanning core cloud infrastructure, large-scale logistics platforms, and applied LLM systems in production. At AWS he was a tech lead for the time-synchronization infrastructure behind EC2. His work centers on complex distributed systems where failures are subtle, silent, and expensive to find.

LinkedIn (opens in new tab)

Roshan Choudhary

Judge

Roshan Choudhary is a Lead Engineer and published technical author specializing in Azure cloud-native development, including serverless architecture, Azure Functions, and AI-augmented workflows, with 14+ years of experience delivering solutions across airlines, finance, and insurance. Based in the Research Triangle Park area of North Carolina, he holds a GitHub Copilot certification (GH-300), OCJP, and OCWCD and authored Azure Functions: From Fundamentals to Production, available free on Google Play.

LinkedIn (opens in new tab)

Jananan Mithrakumar

Judge

Jana Mithrakumar is a Stanford EE alum, former AI accelerator chip designer, and YC founder currently working in consumer AI. His work focuses on building and scaling production AI products, with his latest app recently crossing 250,000 users and over $1M in ARR.

LinkedIn (opens in new tab)

Janushi Shastri

Judge

Janushi Shastri is an AI/ML Engineer and AI Lead at NSV Inc., specializing in medical AI with production experience building clinical AI systems for cervical cancer screening and oral cancer detection deployed across Kenya, Zimbabwe, UK, and India, including collaboration with WHO/IARC experts. She holds an IEEE publication in medical imaging AI and has expertise in deep learning, computer vision, model validation, uncertainty estimation, and responsible AI.

LinkedIn (opens in new tab)

Dheeraj Reddy Pailla

Judge

Dheeraj Reddy Pailla is a published researcher in multimodal deep learning and AI systems (ACM Web Science 2021; IEEE/CVF ICCV 2019; AAAI ICWSM 2020; 1,729 citations) and Senior Software Engineer at Sam's Club / Walmart Global Technology building AI infrastructure for tens of millions of U.S. members.

LinkedIn (opens in new tab)

Anchit Jhingan

Judge

Anchit Jhingan is a Senior Data Scientist with over 6 years of experience in big tech, specializing in machine learning, AI systems, and analytics. He currently works at Amazon Prime Video in the content localization domain. His work focuses on building intelligent systems to solve real-world business problems, particularly in media and entertainment.

Jason Dsouza

Judge

Jason is a senior engineer and independent AI researcher specializing in Computer Vision and AI Safety. He has previously built a popular open-source Computer Vision project and continues to work on practical, real-world applications of advanced AI systems.

LinkedIn (opens in new tab)

Vashishtha Patil

Judge

Vashishtha Patil is a Senior Applied Scientist at Amazon, developing the next generation of LLM-powered AI capabilities for the Alexa+ Smart Home experience. With 13 years in machine learning spanning Amazon and Qualcomm, he specializes in bringing AI from research to real-world products.

LinkedIn (opens in new tab)

Arun Aalla

Judge

Arun Aalla is an Applied AI Architect specializing in enterprise AI solutions, with expertise in large language models, agentic AI, and intelligent automation. He partners with organizations to design and deliver scalable, production-ready AI systems that solve complex business challenges and create measurable impact.

LinkedIn (opens in new tab)

Ankit Pandey

Judge

Ankit Pandey is a sales executive focused on driving business transformation and growth through Cloud, Data & AI. With more than a decade of enterprise sales and client-partner experience (new-logo acquisition, account strategy, and GTM partnerships), he has helped C-suite and senior IT leaders convert digital ambition into measurable outcomes across BFSI, retail/e-commerce, healthcare and more. He has an MBA from GWU with advanced credentials in data analytics and practical certifications in cloud and enterprise tools.

LinkedIn (opens in new tab)

Organizers

Alfie Lamerton

Organizer

Alfie Lamerton is an AI safety researcher building Formation Research, an organization focusing on lock-in risks from AI systems. His research covers AI-enabled totalitarianism, authoritarianism, coups, and power concentration, and governance-informed technical methods for designing and governing AI systems in ways that reduce those risks. He is a co-author of the model-organism work on narrow secret loyalties that this hackathon builds on.

Website (opens in new tab)

Joe Kwon

Organizer

Joe Kwon is an Astra Fellow working with Tom Davidson and Fabien Roger on secretly loyal AI, and the corresponding author of the research agenda behind this hackathon. His work spans AI safety and governance, with a focus on risks from internal deployment, automated R&D, and concentration of power. He previously researched moral cognition at MIT's Computational Cognitive Science Lab, worked on multilingual LLMs at LG AI Research, and studied computer science and psychology at Yale.

Website (opens in new tab)

Kamil Alaa

Organizer

Operations at Apart Research, runs the hackathons and research sprints.

LinkedIn (opens in new tab)

Local sites

Where a Sprint can lead

How our programs connect
  1. Sprint

    Anyone can join

    Stand out

  2. Apart Fellowship

    6 to 16 weeks on your own project, with a research project manager, compute and publication support.