We study AI alignment through the lens of law-and-economics models of deterrence and enforcement. In these models, misconduct is not treated as an external failure, but as a strategic response to incentives: an actor weighs the gain from violation against the probability of detection and the severity of punishment. We argue that the same logic arises naturally in agentic AI pipelines. A solver may benefit from producing a persuasive but incorrect answer, hiding uncertainty, or exploiting spurious shortcuts, while an auditor or verifier must decide whether costly monitoring is worthwhile. Alignment is therefore a fixed-point problem: stronger penalties may deter solver misbehavior, but they can also reduce the auditor's incentive to inspect, since auditing then mainly incurs cost on a population that appears increasingly aligned. This perspective also changes what should count as a post-training signal. Standard feedback often attaches reward to the final answer alone, but a solver-auditor pipeline exposes the full correction event: whether the solver erred, whether the auditor inspected, whether the error was caught, and whether oversight incentives remained active. We formalize this interaction in a two-agent model in which a principal chooses rewards over joint correction outcomes, inducing both solver behavior and auditor monitoring. Reward design is therefore a bilevel optimization problem: rewards are judged not by their immediate semantic meaning, but by the behavioral equilibrium they induce. We propose a bandit-based outer-loop procedure for searching over reward profiles using noisy interaction feedback. Experiments on an LLM coding pipeline show that adaptive reward profiles can maintain useful oversight pressure and improve principal-aligned outcomes relative to static hand-designed rewards, including a substantial reduction in hallucinated incorrect attempts.
\emph{Trapdoored matrices} are pseudorandom matrices admitting a fast matrix-vector multiplication algorithm given the secret key. We study a candidate family of such matrices: matrices generated by short random \emph{transvection walks} on \(\mathrm{SL}_n(\mathbb{F}_q)\), whose steps are given by adding a random multiple of a random row of the current state to another. We show that the worst-case time for any nonempty set \(\mathcal{S}\subseteq [n]\times[n]\) of matrix entries to come within TV distance \(\varepsilon\leq \frac{1}{4}\) of its stationary marginal under this walk is \(Θ(|\mathcal{S}|+n\log(n/\varepsilon))\), uniformly over all \(\mathcal{S}\) and \(q\geq Q_\mathrm{all}(n)\). This is asymptotically optimal, and resolves open questions about the mixing times of transvection walks. We derive concrete upper and lower bounds for \(n\geq 256\). Surprisingly, our bounds also hold conditioned on the row-pair structure of the walk, except on a fraction at most \(\varepsilon\) of such structures. This implies that these walks may be pseudorandom even after conditioning on the row-pair structure, and therefore that trapdoored matrices built with these walks may be universal. Assuming the conjectured structure-conditioned pseudorandomness of short walks, we exhibit highly efficient, highly parallelizable, and universal trapdoored matrices over \(\mathrm{SL}_n(\mathbb{F}_q)\), \(\mathrm{GL}_n(\mathbb{F}_q)\), and \(\mathbb{F}_q^{n\times n}\). The families over \(\mathrm{SL}_n(\mathbb{F}_q)\) and \(\mathrm{GL}_n(\mathbb{F}_q)\) admit equally efficient trapdoors for their inverses, making them the first to do so for finite-field trapdoored matrices. We discuss attacks, analyzing one in detail, and lay out directions for further investigation.