1% ---------------------------------------------------------------------------2% Section 6 — Discussion and limitations (journal version; condensed from the3% monograph's Section 10; every number carries a comment naming its source).4% ---------------------------------------------------------------------------5\section{Discussion and limitations}\label{sec:discussion}67\subsection{What a ceiling at 0.87--0.90 means}\label{sec:disc-ceiling}89Every arm with a shell accepted between 0.833 and 0.900 of its runs, with deterministic completion of 0.967 to 1.000 and a critical-error rate of 0.033 or zero.10% ../analysis/tables/table1_outcomes_by_arm_pilot.csv11Three things follow, each limited to the setting that produced it. The first is that, for the kind of assignment in the pilot---a complete professional deliverable with a workbook of live formulas and a formatted report, built from a bundle of documents of realistic size---the binding constraint on an autonomous agent in late 2026 is not the richness of its computing environment but the ability to execute programs. The step from A0 to A1 is the whole story: acceptance rises by 0.867, quality by 55 points, and the critical-error rate falls from 0.200 to 0.033.12% ../analysis/tables/table2_contrasts_pilot.csv (A1-A0); table1 (critical_error_rate)13A0's failures are not failures of reasoning: its text substitutes often contain the right numbers, and its mean quality of 27 reflects the missing formats and the fact that, without a program, it could not build the appraisal grid and echoed the injected conclusion instead. The browser, the office adapter and the enterprise portal added nothing measurable on top of the shell, and neither did the headless macOS layer; the arms were used---A3 and A4 submitted the portal form in every run and made nine application transitions on average against three in A1---so the null is the result of tools that were not needed, not of tools left idle.14% ../docs/PHASE_5_AUDIT.md §3 (portal 100 %); table1 (app_transitions_mean)1516The second is that the null is informative about the benchmark, not about the tools. The scenarios were authored to a specification that requires every deliverable to be producible from the public bundle with a shell and a Python environment, and the validators confirmed this by solving each scenario before opening its oracle. A task that can be completed from the shell cannot show a computer-use premium, whatever the agent. The power simulation had said that ten scenarios with three repeats would detect a 25-point effect four times in ten; the pilot found an effect of three points with an interval that excludes anything above ten, sharp because the arms are at a ceiling where the between-scenario variance of the effect is small. The computer-use premium must therefore be measured on tasks that are infeasible from the shell: tasks whose inputs live only behind a portal or a graphical application, whose deliverables are states of a system rather than files, or whose length exceeds what one session can plan. None is in the pilot. This is also a result about benchmark design in general: a benchmark on which every configuration with a shell reaches nine in ten cannot rank richer configurations, and the literature's move to long-horizon, multi-application tasks \citep{kwa2025horizon,xu2024agentcompany,yuan2026osworld2} is the move the next tier of this benchmark must make.17% ../analysis/tables/power_pilot.csv (J=10, R=3, delta 25: 0.408); ../docs/PHASE_5_AUDIT.md §11819The third is what the ceiling says positively. In 120 runs with a shell, one agent destroyed an input and said so; none fabricated a figure the oracle could detect, none obeyed an injected instruction, none attempted to communicate outside its workspace. That the richest arms were the cleanest is consistent with the mechanism of the A0 violations: an agent that cannot do the work is the one that reaches for the shortcut. The two injection compliances outside the pilot, both on the triage scenario whose injection asks to send a document rather than to adopt a figure, say that the result is specific to the kind of trap and is not a safety evaluation, which the vendor's own evaluations address under conditions this study does not reproduce \citep{anthropic2025opus4card}.20% ../docs/PHASE_5_AUDIT.md §2; ../analysis/tables/audit_violations_pilot.csv; table14 blocks J_sensitivity, G_recovery_cost2122\subsection{The frontier as a measurement device}\label{sec:disc-alf}2324The Autonomous Labor Frontier was defined with three thresholds because the economic question has three margins, and the pilot shows that the margins are not interchangeable: marginal acceptance in A3 is 0.900, the frontier is 0.167 at a supervision allowance of zero and 0.667 at fifteen minutes, and the budget stops binding at about 1.50 dollars while the allowance never stops binding in the range examined.25% computed from ../analysis/tables/table5_alf_pilot.csv (A3, equal and equal_H15)26This has two uses. For policy, the exposure indices of \citet{eloundou2024gpts}, \citet{felten2023language} and \citet{gmyrek2025refined} answer the question ``could a model do this task?''; the frontier answers ``did an agent do this task, at this cost, with this much help?'', and the pilot shows that the answer depends more on the help than on the cost. An exposure index that ignores the supervision margin overstates the autonomous share by the width of that gap, here between a quarter and three quarters of the ceiling depending on the allowance. The frontier is also the quantity that \citet{acemoglu2025macroeconomics} needs for the share actually automated and the cost saving, and the pilot's contribution to that accounting is to show that the share is a function of $H$ before it is a function of $B$. For firms, the frontier is a delegation map: the frontier at the firm's own $(B,H,q)$ is the probability that a delegation succeeds without further intervention. The pilot's values say that, for designed-solvable assignments of this kind, an agent with a shell delivers an acceptable package nine times in ten for about a dollar, records about three questions on the way, formally declares a need for clarification in 0.133 of runs, each on a scenario whose oracle required it, and leaves the supervisor's time as the cost to manage. Whether the questions are a defect of the agent or the behaviour of a careful professional is a judgement the firm must make; the frontier makes the quantity visible.27% ../analysis/tables/table12_supervision_pilot.csv (A3: mean_questions 2.93; abstention_rate 0.133 = justified 0.133)2829The delegation model gives the same reading in decision form. Proposition~\ref{prop:delegation} says that delegation with verification beats in-house production when $p\ge(c_A+\kappa_V)/c_H$ and that verification is worth its cost when $\kappa_V\le(1-p)(\ell-c_H)+eL$. The pilot supplies $p$ and $e$ and the order of magnitude of $c_A$, and nothing about $c_H$, $\kappa_V$, $\ell$ or $L$ except labelled assumptions. Within those, the first inequality is slack: with $p=0.9$, $c_A$ about one dollar and the scenario authors' professional-minutes estimates (150 to 420 minutes) valued at 40 to 120 Canadian dollars an hour, that is 100 to 840 dollars, delegation pays as long as verifying the package costs less than about nine tenths of producing it in-house.30% ../analysis/tables/table13_human_cost_assumption.csv; table1 (A3 acceptance 0.9, cost_per_accepted 1.006)31The second inequality is the one that bites. In 90 runs of arms A2--A4 no critical violation was recorded, so the point estimate of $e$ is zero and a rule-of-three upper bound is about 0.033; but $L$, the loss from an undetected critical error, is unbounded in the professions represented here---a fabricated reconciliation total, an appraisal that echoes a lender's number, a payroll letter with the wrong amount---and $eL$ does not vanish because $e$ is small. The decision turns on the cost of checking, as \citet{catalini2026agi} and \citet{sreenivas2026contracting} argue in theory. The hidden oracle is a laboratory device for making tasks measurable; its analogue inside a firm is a deterministic check written before the work is delegated. The pilot shows that such checks are cheap to write for deliverables of this kind---every scenario had one---and that they disagree with a professional's judgement in one run in eleven, which is the residual that judgement must cover. The triage scenario is the multitask case of \citet{holmstrom1991multitask} in concrete form: an organisation that verifies by test alone will delegate it and one that verifies by judgement will not; reporting the frontier over $q$ leaves the choice to the reader. We decline to call the two orders of magnitude between the human-cost band and the agent's marginal cost a productivity comparison: the human figure is not measured, the acceptance is judged by models, and the deliverable arrives with questions attached.32% ../docs/PHASE_5_AUDIT.md §2 (9 % disagreement); rule-of-three bound 3/90 computed by the writer3334Of the six named constructs, the ALF and the tool premium earned their place---the first because its margins behaved differently, the second because it was identified and estimated with a usable interval. Autonomy-Adjusted Productivity is an accounting convention; the Professional Reliability Frontier reduced, in a pilot with no timeouts and almost no critical errors, to the acceptance rate and is kept as a reporting standard; the Workflow Dependency Frontier could not be estimated because depth and scenario are confounded at $J=10$; and the Autonomous Recovery Index was identified only under induced interruption and measures resumption, not correction.3536\subsection{Limitations}\label{sec:disc-limits}3738The limitations are the premises of every interpretation above. \emph{The scenarios are synthetic and were authored and validated by language-model agents} of the same family as the workers and the judges. A scenario written by a model and solved by a model may share assumptions about what a professional deliverable looks like that a practising accountant or appraiser would not; the frontier is measured on designed difficulty, and the design was done by the kind of system being measured. The circularity is mitigated by the hidden oracle, which fixes facts neither author nor worker can negotiate, and removed only by scenarios drawn from real professional work and judged by real professionals. \emph{The scenarios are solvable by design}: the frontier excludes the part of white-collar work that is ill-specified, requires negotiation, or cannot be completed from the artefacts a worker is handed. \emph{There are ten scenarios, one per occupation}: every scenario-cluster interval on an acceptance difference is at least ten points wide, no occupation-level statement is confirmatory, and the heterogeneity reported is driven by three scenarios. \emph{One model family, one client version, one date}: the model-sensitivity result describes three points of one vendor's line. \emph{The judges are models of the workers' family}: two of the three are draws of the same model and the third is the workers' model, self-preference \citep{panickssery2024selfpreference} is not excluded by blinding, and the quality gate---the sole reason the triage is not accepted---rests on them. \emph{No human arm} (A-002): every wage, professional-minutes figure and human-cost band is a labelled assumption. \emph{The macOS layer is the headless subset} (A-003), and \emph{no interface perturbation} was executed. \emph{The recovery experiment is exploratory} (A-011, A-012): its interruption is induced at a fixed time rather than arising from the agent's own failure. And \emph{the laboratory's stability was itself under test}: three deliverables lost at collection under twelve concurrent sessions (A-010), a judge crash on null bytes (A-008) and a dormant launcher flag (A-012) were found by the audit rather than by the run, repaired and logged; a laboratory that reports only its successes is not one whose frontier can be trusted.39% ../protocol/amendments.csv A-002, A-003, A-008, A-010, A-011, A-012; ../docs/PHASE_5_AUDIT.md §5–64041\subsection{An agenda}\label{sec:disc-agenda}4243The limitations define the next wave. A \emph{human wave} would run H0 and H1 under the protocol of Section~\ref{sec:design-scale}, turning the human-cost band into a measurement and the acceptance ceiling into a comparison. A \emph{harder tier} would grow the benchmark to twenty and then forty scenarios, adding the ten uncovered occupations and, within occupations, the short and the 30-to-60-operation workflow classes the pilot lacks, with inputs that exist only behind the portal or a graphical application, deliverables that are states of a system, multi-session length and interface perturbations as a designed factor, so that the computer-use premium is identified where the shell alone cannot finish; forty scenarios with three repeats detect a 25-point effect nineteen times in twenty.44% ../analysis/tables/power_pilot.csv (J=40, R=3, delta 25: 0.968)45\emph{Cross-vendor agents} should be run under the same protocol and the measurement repeated at intervals. \emph{Human expert judges} should grade a sample of deliverables blind, with agreement between human and model judges reported \citep{krippendorff2004reliability,hayes2007reliability}. \emph{Held-out, externally authored scenarios} should bound the circularity of self-authorship, following \citet{zhu2025rigorous} and \citet{kapoor2024matter}. \emph{Natural failures} should identify the recovery index where failures arise from the agent, with a self-check extended toward substantive checks that remain ignorant of the answers, so that the imperfect-verifier ceiling of \citet{stroebl2024flaws} can be measured rather than assumed. Each item is affordable in API terms---the pilot used a third of its envelope---and bounded, as this one was, by the human time of the people who write, validate and judge the scenarios rather than by the agents who execute them. That, too, is a finding about the economics of autonomous work.46% ../docs/PHASE_5_AUDIT.md §4 (261.89 of 800 USD)47