Skip to content
Apart Research
Apart Research
Contact us
Sprint projectFeb 2, 2026Dallas

AI Safety Threshold Tracker

Revathi Prasad · Team AI Safety Threshold Tracker

Submitted to The Technical AI Governance Challenge. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: AI Safety Threshold Tracker

Open in a new tab (opens in new tab)
Code (opens in new tab)
Share

AI Safety Threshold Tracker An interactive dashboard that connects AI capability benchmarks to governance-defined thresholds. The tracker aggregates verified data from third-party evaluations (METR, SWE-Bench, WMDP) and company RSP disclosures (Anthropic ASL classifications, CBRN uplift scores), mapping them to thresholds derived from international frameworks including IDAIS Red Lines, EU AI Act, and Seoul Summit commitments.

Key features: 1. User-configurable thresholds with transparent justification labeling (distinguishing data-driven thresholds from interpretations) 2. 4 active capability metrics, 2 categorical RSP metrics, 5 inactive metrics awaiting data 3. Real-time tracking of frontier model capabilities against policy-relevant thresholds

Reviews

Judging this Sprint?

Review this project

Your public critique appears on this page without your name. Your private critique is not published; only the Apart team reads it. If you agree below, we share your review with grantmaking.ai (opens in new tab) and the Transformative AI Fund so strong projects can be funded.

Not shown on this page.

Shown on this page, without your name.

Only the Apart team reads this, and funders if you agree below.

Share my name publicly on grantmaking.ai *
Share my private critique with funders *

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?

Scoring guide
  1. 1Negligible. No clear problem addressed, or no meaningful novelty.
  2. 2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
  3. 3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
  4. 4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
  5. 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.

How sound are methodology, implementation, and findings?

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

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

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

  1. A useful tool with a simple idea. Only a few models has been tested which is reasonable given the time constrains.

  2. This is a practical project that fills a real gap: turning vague “threshold” talk into something you can actually track. The framing is sensible and the dashboard is clear.

    The main limitation is that the threshold mappings are still somewhat heuristic. This is more “good governance plumbing” than a new safety method. The impact depends on adoption.

    To level up, I’d want: backtesting (“would this have changed decisions historically?”), uncertainty / missing-data handling, and a clean process for updating thresholds without Goodharting.

Cite this project

@misc{prasad2026ai,
  title = {{AI Safety Threshold Tracker}},
  author = {Revathi Prasad},
  year = {2026},
  month = feb,
  note = {Submitted to The Technical AI Governance Challenge, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/ai-safety-threshold-tracker-fnxw}},
  url = {https://apartresearch.com/sprints/projects/ai-safety-threshold-tracker-fnxw}
}

More from The Technical AI Governance Challenge

All 47 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026