> ## Content Index > Fetch the complete content index at: https://modalpathethics.com/llms.txt > Use this file to discover other available public pages before exploring further. # Convergence Point: Sławomir Krakowski and the Correction That Can No Longer Arrive - URL: https://modalpathethics.com/convergence-point-slawomir-krakowski-and-the-correction-that-can-no-longer-arrive/ - Published: 2026-10-05T11:00:53.000Z - Updated: 2026-10-05T19:01:16.000Z - Description: A right to correct is not a path by which correction remains possible. - Author: Aidan Lawson - Tags: Convergence Point, Engagement, Modal Systems, Instrument Jurisdiction, Security Instruments ## The Dates Come First. Before the theory, the chronology. Because this one is close enough that the chronology has to do actual work. - **14 April 2026:** a public Zenodo record appears for Sławomir Krakowski's *Symformism: An Ontology of Enduring Forms*. The project is already concerned with persistence, organization, recovery, and how enduring structures alter what can happen next. ([TGRS](https://globalresearchspace.com/space?star=W7154472628&utm%5Fsource=chatgpt.com)) - **15 April:** modalpathethics.com begins publishing. The book manuscript had been sent to friends as finished on April 4, but that is retrospective self-documentation, so I am not going to use it as a public priority weapon. The public site begins on the **15th**. ([Modal Path Ethics](https://modalpathethics.com/coming-soon/?utm%5Fsource=chatgpt.com)) - **7 May:** [*Formal: Contraction Is Harm*](https://modalpathethics.com/contraction-is-harm/). - **9 May:** [*Formal: Weighted Reachable Future Space*](https://modalpathethics.com/formal-weighted-reachable-future-space/) and [*Formal: What Makes Something a Locus*](https://modalpathethics.com/formal-what-makes-something-a-locus/). - **11 May:** [*Formal: Resistance and Harm*](https://modalpathethics.com/formal-resistance-and-harm/) distinguishes a formally available path from a path that remains materially reachable. - **3 September:** Krakowski posts *Measuring Lost Futures: A Layered Reachability Model for Adaptive Systems*, written September 2\. It defines an **architecture of possibility** around viable future configurations and the routes by which they remain reachable. ([SSRN](https://papers.ssrn.com/sol3/papers.cfm?abstract%5Fid=7394838&utm%5Fsource=chatgpt.com)) - **10 September:** Krakowski posts *Primary Field Cybernetics*, written August 30\. Its central proposition is that control depends not merely on choosing actions but on preserving the conditions under which viable future action remains accessible. **The same day**, Modal Path Ethics publishes *The Death of an Office*: authority must be able to disappear while the function survives. ([SSRN](https://papers.ssrn.com/sol3/papers.cfm?abstract%5Fid=7442820&utm%5Fsource=chatgpt.com)) - **18 September:** *Applied Case: The Dog Gets the Ball* introduces the **corrigibility horizon**: the point at which formal removal remains available while adequate independent replacement can no longer arrive inside the protected correction interval. ([Modal Path Ethics](https://modalpathethics.com/articles/?utm%5Fsource=chatgpt.com)) - **19 September:** Krakowski dates *Decision Closure: Structural Reachability and the Cost of Correction*. It separates **structural reachability** from **correction impedance** and asks how institutional structure can make correction unavailable even after failure has been recognized. It is posted on September 22\. ([SSRN](https://papers.ssrn.com/sol3/Delivery.cfm/7489739.pdf?abstractid=7489739&mirid=1&type=2&utm%5Fsource=chatgpt.com)) - **20 September:** *Harm as Contraction* v1.2 goes public on Zenodo and the accompanying article states the bridge explicitly: **correction is itself a reachable continuation**, and formal corrigibility can survive after material corrigibility has died. ([Modal Path Ethics](https://modalpathethics.com/artificial-intelligence-needs-a-structural-ethics-layer/?utm%5Fsource=chatgpt.com)) - **3 October:** Krakowski posts the paper that finally triggered this article: ***Autonomous Weapon Systems—Beyond Human-in-the-Loop: Correction Reachability and the Closure of Futures***. SSRN records 34 pages posted October 3\. ([SSRN](https://papers.ssrn.com/sol3/papers.cfm?abstract%5Fid=7552581&utm%5Fsource=chatgpt.com)) Do not cheat with these dates. The September sequence is almost **comically** interleaved. There is presently no evidence I have found of influence in either direction. So **this is not a priority claim**. We are not doing priority theater in Convergence Point. Now we can talk about the much stranger thing that actually happened. --- ## Krakowski Found the Correction Path. The autonomous-weapons paper begins with a fairly ordinary governance question. - A human is supervising an autonomous system. > **Can the human still stop it?** Krakowski immediately rejects the easy version of that question. A human can retain authorization. The stop command can exist. The communication architecture can formally contain an intervention channel. The system can still be called human-supervised. And the correction can already be gone. His question is: > **once evidence of error becomes available, does a viable corrective trajectory still exist?** He calls the property **correction reachability**. Then he formalizes it. - Let the system occupy some state. - Let there be a set of interventions actually available under the relevant communication, permission, physical, and temporal constraints. - Let there be some admissible safe set. - Correction exists only if an available intervention can still carry the system into that safe set. Not: > Is somebody authorized to intervene? Not: > Is there technically a stop command? Not: > Is the human still in the diagram? But: > **Can correction still get from here to there?** That distinction should be extremely familiar around here. Krakowski states it plainly: > control authority is not the same as control capability. Formal supervisory authority can remain intact while the viable correction set collapses underneath it. There you are. --- ## A Right Is Not a Path. Modal Path Ethics arrived at the same structural problem through institutions. A tenant can possess an appeal that cannot be survived. A regulator can retain jurisdiction over infrastructure it can no longer reach in time. An organization can retain the contractual right to replace an AI system after records, interfaces, expertise, workload, and dependencies have made replacement operationally catastrophic. - The formal option remains. - The reachable continuation underneath the option dies. That was the point of **resistance** back in May. Then it became the point of **material bounded finality** in September. Krakowski gets there through **machine-speed control**. He decomposes the correction process into time required to: - detect the problem, - interpret it, - choose a correction, - transmit and execute it, against the time remaining before the relevant transition becomes effectively irreversible. The command can still exist after the time required to use it has become longer than the world will wait. At that point the **right** survives. The **path** does not. This is not an analogy we have to force onto Krakowski's paper. That is the object he is measuring --- ## Then He Starts Closing Futures. Correction reachability would already be enough for a Convergence Point. Then Section 10 arrives. Krakowski defines a set of strategically admissible future trajectories and a corresponding **reachable-future volume**. An action is **future-closing** when that volume decreases. He distinguishes three forms of closure. 1. **Global closure**: the relevant safe reachable set is exhausted. 2. **Partial closure**: materially important classes of response disappear while others remain. 3. **Operational closure**: alternatives still exist abstractly, but no longer remain executable inside the available time, resources, permissions, or communication envelope. That third category is the important one. Because it kills one of the most persistent bad arguments in governance: > But technically you still **could**. Yes. Technically the future remains describable. The question is whether anything extant can still reach it. Krakowski then characterizes autonomous escalation as a process in which machine-speed interaction **closes reachable futures faster than command structures can preserve or restore them**. And he identifies what changes as not just reaction time, but: > **the topology of available correction.** That is a ***Convergence Point***. --- ## Accuracy Is Not Corrigibility. Then Krakowski does something even more useful. He tests it. His first simulation compares three architectures: - action-level human authorization; - continuous interruptible supervision; - second-order bounded autonomy. The interesting result is that **classification accuracy** stays high across all three. **Correction reachability** does not. The second-order bounded architecture preserves substantially more correction space while reducing unsafe terminal outcomes, even in matched cases where classification accuracy is almost the same. That gives us a clean separation: > **Being right often is not the same property as remaining correctable when wrong.** Good. This is exactly why a benchmark score cannot certify a constitutional architecture. Then he performs an ablation. Under increasing uncertainty, an architecture allowed to make **graded commitments** instead of immediately committing at full strength preserves more reachable correction space. At the highest modeled ambiguity, the staged version reduces unsafe terminal outcomes and retains a larger correction set. Krakowski properly labels this a model-internal result rather than pretending he has measured the battlefield. The underlying principle is simple: > The less certain you are, the less of the future you should irreversibly consume. I am extremely comfortable with that sentence. --- ## The Human Can Keep the Job After Losing the Power. The second experiment is even closer. Krakowski keeps the nominal supervisory architecture unchanged. The human is still the **human-on-the-loop**. Then he degrades sensing and communication. - Nothing changes in the org chart. - Everything changes in the causal graph. Under favorable communications, most issued interventions arrive. Under poor communications, fewer than a third do. The human has not lost authority. The intervention has lost reach. This produces one of the paper's strongest distinctions: - **command availability,** - **command executability,** - **effective correction** are not the same thing. A human role can remain formally unchanged while becoming causally useless. --- ## The Future Can Also Remember What Corrected It. Krakowski then adds **correction memory**. An adaptive system does not just retain prior states or policies. It can retain the history of how its policies were changed after errors, exceptions, overrides, and interventions. Two initially identical systems can therefore become different systems after different correction histories. More importantly, an organization can possess every historical log and still lack the practical capacity to reproduce the corrective competence embodied in the resulting policy. Krakowski says this explicitly: > **Mere ownership of logs does not guarantee control of the learned capability.** This is smaller than the provenance problem Modal Path Ethics has been pursuing. But it is the same warning. The record of a transformation is not automatically the capacity carried by the transformed thing. - Transfer the archive. - Lose the function. Congratulations. You preserved the receipts for the dead path. --- ## Then He Tries to Break It. This is the part that makes the paper materially better. Krakowski hypothesizes that increasing coupling among autonomous agents might generically accelerate future closure. His simulation does not support the strong claim. So he rejects it. Coupling alone does not reliably produce escalating closure in the model. Supervisory damping, recovery authority, asymmetric response, and belief decay can interrupt the process. A narrower result survives. Actual **reciprocal reaction chains**[—](https://modalpathethics.com/gizmodo-has-13-116-new-ways-to-accuse-gizmodo-of-using-ai/)where agents respond to a world increasingly constituted by one another's preceding actions—are associated with much sharper contraction of reachable future-space. So the claim gets smaller. The framework also provides explicit falsification conditions and says it should be weakened or rejected where the predicted mechanisms fail. This is how you are supposed to treat your favorite abstraction. - Do not make reality defend the theory. - Make the theory survive reality. --- ## **Convergence Point.** We can now state the collision without flattening either project. - Krakowski's **correction reachability** and Modal Path Ethics' **material corrigibility** both reject formal authority as sufficient evidence that correction remains available. - Krakowski's **reachable-future closure** and Modal Path Ethics' **contraction** both describe present transitions by what they remove from the practically reachable future. - Krakowski's **operational closure** and Modal Path Ethics' **resistance / material reachability** both distinguish abstractly describable alternatives from alternatives an extant system can actually still reach. - Krakowski's **correction memory** and Modal Path Ethics' historical field both reject the idea that the present state alone fully describes later possibility. - Krakowski's second-order control and Modal Path Ethics' bounded-finality work both move the safety question upstream: do not merely preserve an emergency command; preserve the conditions under which consequential correction can still occur when the emergency arrives. The shared rejection is extremely simple: > **A correction that exists only in description is not yet an available correction.** And underneath that: > **What matters about a system now includes whether it can still become otherwise later.** That is the convergence. Now we have to separate the theories. --- ## The Safe Set: Not Yet an Ethics. Krakowski defines the admissible safe region as an intersection of physical, operational, legal, and strategic constraints. That is exactly what a systems paper should do. He also explicitly says the mathematics does not determine what counts as acceptable. Different components of the safe set come from different expertise and authorities. And here Modal Path Ethics walks into the room. Because: > **Who defined the safe set?** > Which loci made it into the model? > Whose continuations count as admissible futures? > Which harms sit outside the military objective? > Which legal rule deserves jurisdiction? > Which strategic goal is being preserved? > What happens when every supervisory instrument successfully preserves a future that is catastrophic for something the architecture never represented? Krakowski's paper does not answer these questions. It does not claim to. **Correction reachability** begins after some relevant notion of acceptable continuation has been specified. Modal Path Ethics is trying to deal with the uglier problem one level earlier: > **What is actually in the field, and which transitions count as damage to it?** That is a real difference. --- ## Specification: Not Automatically Harm. There is another important agreement hiding inside a difference. Krakowski explicitly warns that not every reduction in reachable-future volume is undesirable. Of course not. A decision necessarily excludes alternatives. A safety boundary should close some paths. A missile that cannot redirect itself toward civilians has lost reachable futures. Modal Path Ethics has the same problem. **More possibility** is not automatically **more good**. A predator's future can be constrained to preserve another locus. A tyrant can lose options. A virus does not receive a moral claim to every continuation its replication can reach. So neither framework can simply worship branch count. - Krakowski handles this by measuring reachability relative to an externally specified safe set. - Modal Path Ethics handles it through loci, weighting, relation, burden, repairability, instrument jurisdiction, and the distinction between harmful contraction and justified protective friction. Same geometry. Different normative machinery. --- ## There Is Still a Responsible Human at the End. Krakowski's architecture ultimately asks whether **responsible human judgment** retains enough causal leverage to alter the trajectory before correction becomes unreachable. That is the right question for his domain. Modal Path Ethics has to ask another one immediately afterward: > **What corrects the responsible human?** - What if the supervising institution chose the wrong safe set? - What if command authority itself is captured? - What if the legal rule is the source of the contraction? - What if the responsible human is perfectly capable of intervening and should not have jurisdiction over the affected locus in the first place? **Material bounded finality** generalizes the object. > The correcting authority must itself remain capable of losing. Otherwise we have preserved corrigibility downstream by installing finality upstream. The stop button works beautifully. Only the person holding it cannot be stopped. --- ## Krakowski Gives Us Something Back. ***Convergence Point*** is useless if it means finding people who happen to sound familiar. Krakowski gives Modal Path Ethics several sharper instruments. - First, **correction margin**. Correction is not simply open or closed. The remaining path has a temporal budget. Detection, interpretation, authorization, transmission, and actuation consume that budget while the world continues moving. Material bounded finality should care about that explicitly. - Second, **correction reachability as a dynamic quantity**. Do not ask only whether replacement or intervention works now. Measure how quickly the available correction set is collapsing. A system can be constitutionally healthy today and already moving rapidly toward dependence tomorrow. - Third, **uncertainty-conditioned reversibility**. If uncertainty increases, do not compensate by committing faster. Preserve more reversibility. That principle travels very well. - Fourth, **accuracy is not corrigibility**. This should be tattooed onto every AI-governance benchmark currently being designed. A system can answer correctly at **extraordinary** rates while building a world in which the remaining errors become impossible to correct. That is not a contradiction. That is the entire problem. --- ## The Ruling. Sławomir Krakowski is a **Convergence Point** interlocutor. The chronology gives us no respectable reason to tell a borrowing story. His Symformism research program was public before the Modal Path Ethics website. Modal Path Ethics then publicly developed contraction, loci, weighted reachable future-space, and resistance in May. Krakowski's later work moved independently into layered reachability, access geometry, decision closure, correction impedance, and finally a formal theory of **correction reachability** and **reachable-future closure**. The strongest versions of the two correction architectures then appear almost on top of one another in September and early October. - Different problem. - Different apparatus. - Different normative scope. - Same structural wound. > Krakowski began with autonomous weapons and asked whether a human who still possesses authority can still reach the future in which the machine is corrected. > Modal Path Ethics began with harm and eventually discovered that correction itself can be one of the futures a system destroys. > Krakowski gives us the systems geometry of the disappearing intervention. > Modal Path Ethics asks who gets standing in the geometry, which contractions count as harm, which instrument may judge them, and whether the correcting authority can itself be corrected. Neither makes the other disappear. The common result is much cleaner than either vocabulary: > **A right to change the future is not the same thing as a future in which change can still arrive.** - The button can remain. - The law can remain. - The supervisor can remain. - The appeal can remain. - The institution can remain. - The future they were supposed to reach can already be gone. That is the ***Convergence Point***.