Skip to content
Apart Research
Apart Research
Contact us
Sprint projectMar 23, 2026Eau Claire

Frankenstein ducks the linear probes

Abhinav Chand, Balaji R · Team Mech Interpers

Submitted to AI Control Hackathon 2026. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: Frankenstein ducks the linear probes

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

Recent work has shown that linear probes are very effective in detecting deceptive behavior of large language models, both pre-generation (intent) and post-generation (harmful content) of LLM’s response . We investigate fine-tuning methods to suppress detection by deception probes. Our results show that we can reduce the detection rate of linear probe monitors with our fine-tuning method.

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. This seems interesting to me as a useful component for doing the red team iteration for a control game where the protocol involves linear probes. This is potentially useful for this.

    One core issue is that this paper's threat model is unrealistic in a way that matters. They train against the exact probe direction they then evaluate on. But in a real deployment, the blue team constructs probes after receiving the model, possibly using different contrast pairs, different layers, or ensembles. The red team doesn't get to see those probes during training. So the paper demonstrates something closer to "you can overfit against a known classifier" rather than "you can make a model that's fundamentally harder to probe."

    I also think this paper could have been condensed.

  2. This project seems very similar to Obfuscated Activations (https://arxiv.org/pdf/2412.09565), with a topical shift to sleeper agents / AI control. The training method degrading sleeper agent behavior as a condition to evade the probe is a weakness, as is the lack of results showing generalization beyond evading the specific probe that was trained against.

    Overall it's good and ambitious work for the scope of a hackathon, but would've benefitted from some more careful literature review + more accurate signposting of the weaknesses of the results. The continuation I'd be most excited for is a demonstration like the iterative monitor evasion result in figure 8 from Obfuscated Activations.

Cite this project

@misc{chand2026frankenstein,
  title = {{Frankenstein ducks the linear probes}},
  author = {Abhinav Chand and Balaji R},
  year = {2026},
  month = mar,
  note = {Submitted to AI Control Hackathon 2026, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/frankenstein-ducks-the-linear-probes-dcz9}},
  url = {https://apartresearch.com/sprints/projects/frankenstein-ducks-the-linear-probes-dcz9}
}

More from AI Control Hackathon 2026

All 125 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026