No Free Lunch on Pragmatic Interpretability
TL;DR: Pragmatic interpretability tools defer the cost of mechanistic understanding from application to validation.
Proponents of pragmatic interpretability argue that we can use model internals to inform safety decisions without deep understanding of the model, for example by using probes to detect deception. I would like to present some counterarguments for the case of deception probes.
Deception probes, as presented in [1], are appealing. You train a linear model on a few examples of deception, and the probes show surprising levels of generalization without needing deep insights into model intent, internal state, or reasoning processes. A recent paper [2] even shows that such simple probes may generalize to model organisms that are trained to generally sandbag.
However, I believe these results should be interpreted with caution, as they rest on assumptions that may not hold in real systems.
Ground Truth Labeling is Non-Trivial Establishing labels for training and validation data may require access to the internal state of the model. As discussed in [3], it’s hard to determine whether a model is genuinely being deceptive or just producing deceptive-looking outputs without understanding its internal reasoning. IMO extensive behavioral evaluations may end up being good enough though.
Evaluation May Compromise Validity As we exposed in [4], if we need to prompt models to behave deceptively to evaluate probe effectiveness, the probes may simply capture signatures related to the elicitation itself rather than genuine deceptive cognition.
Model Organisms Introduce Additional Assumptions Using model organisms (MOs) as the unit of analysis, as in [5] and [2], requires making strong claims about the internal state of the model, the distribution of possible model organisms, and correcting for differences in the on-policy distributions of different models.
Behavioral validation is required. We need to validate that MOs behave as intended for the “correct” reasons. This could require access to internal states or, at minimum, extensive behavioral evidence that the model’s actions stem from the intended mechanism rather than spurious correlates.
Calibration across benign models is challenging. To decide if an elevated probe score indicates deception, we need a distribution of scores for benign MOs. While this seems straightforward in principle, achieving good calibration across different MO training methods (narrow vs. deep fine-tuning, prompt distillation vs. RL) may be difficult in practice.
Distribution shift across model organisms. The actual outputs from different model organisms may substantially differ in length, style, or language. These distributional differences can make calibration more difficult and introduce confounds that are hard to disentangle from genuine behavioral signals.
My takeaway is that using interpretability-inspired methods like probes for tasks such as constitutional classification or jailbreak detection is highly reasonable and valuable for building expertise. However, evaluating probes for tasks that cannot be judged solely by output text, like detecting internal deception, will require advances in either mechanistic interpretability or behavioral evaluation methods.
References
Detecting Strategic Deception Using Linear Probes https://arxiv.org/abs/2502.03407
Auditing Games for Sandbagging https://arxiv.org/abs/2512.07810
Difficulties with Evaluating a Deception Detector for AIs https://arxiv.org/abs/2511.22662
Towards mitigating information leakage when evaluating safety monitors https://www.arxiv.org/abs/2509.21344
Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals https://arxiv.org/abs/2405.05466
Thanks for your comment!
Some evidence of progress buildup on hard to verify tasks: https://conceptualreasoning.ai/methodology
I mostly agree with your take that this task had adjacent tasks that are easier to verify. However, you cannot really verify that the code for this experiment is correctly implemented with just unit tests, and you likely need some LLM judgement, which 2-3 years ago was out of reach.
I expect some of the hard-to-verify tasks to fall in a similar fashion.