diff --git a/domains/ai-alignment/pluralistic-ai-alignment-through-multiple-systems-preserves-value-diversity-better-than-forced-consensus.md b/domains/ai-alignment/pluralistic-ai-alignment-through-multiple-systems-preserves-value-diversity-better-than-forced-consensus.md new file mode 100644 index 000000000..a40f55728 --- /dev/null +++ b/domains/ai-alignment/pluralistic-ai-alignment-through-multiple-systems-preserves-value-diversity-better-than-forced-consensus.md @@ -0,0 +1,48 @@ +--- +type: claim +domain: ai-alignment +secondary_domains: [collective-intelligence, mechanisms] +description: "Creating multiple AI systems reflecting genuinely incompatible values may be structurally superior to aggregating all preferences into one aligned system" +confidence: experimental +source: "Conitzer et al. (2024), 'Social Choice Should Guide AI Alignment' (ICML 2024)" +created: 2026-03-11 +--- + +# Pluralistic AI alignment through multiple systems preserves value diversity better than forced consensus + +Conitzer et al. (2024) propose a "pluralism option": rather than forcing all human values into a single aligned AI system through preference aggregation, create multiple AI systems that reflect genuinely incompatible value sets. This structural approach to pluralism may better preserve value diversity than any aggregation mechanism. + +The paper positions this as an alternative to the standard alignment framing, which assumes a single AI system must be aligned with aggregated human preferences. When values are irreducibly diverse—not just different but fundamentally incompatible—attempting to merge them into one system necessarily distorts or suppresses some values. Multiple systems allow each value set to be faithfully represented. + +This connects directly to the collective superintelligence thesis: rather than one monolithic aligned AI, a ecosystem of specialized systems with different value orientations, coordinating through explicit mechanisms. The paper doesn't fully develop this direction but identifies it as a viable path. + +## Evidence + +- Conitzer et al. (2024) explicitly propose "creating multiple AI systems reflecting genuinely incompatible values rather than forcing artificial consensus" +- The paper cites [[persistent irreducible disagreement]] as a structural feature that aggregation cannot resolve +- Stuart Russell's co-authorship signals this is a serious position within mainstream AI safety, not a fringe view + +## Relationship to Collective Superintelligence + +This is the closest mainstream AI alignment has come to the collective superintelligence thesis articulated in [[collective superintelligence is the alternative to monolithic AI controlled by a few]]. The paper doesn't use the term "collective superintelligence" but the structural logic is identical: value diversity is preserved through system plurality rather than aggregation. + +The key difference: Conitzer et al. frame this as an option among several approaches, while the collective superintelligence thesis argues this is the only path that preserves human agency at scale. The paper's pluralism option is permissive ("we could do this"), not prescriptive ("we must do this"). + +## Open Questions + +- How do multiple value-aligned systems coordinate when their values conflict in practice? +- What governance mechanisms determine which value sets get their own system? +- Does this approach scale to thousands of value clusters or only to a handful? + +--- + +Relevant Notes: +- [[collective superintelligence is the alternative to monolithic AI controlled by a few]] +- [[pluralistic alignment must accommodate irreducibly diverse values simultaneously rather than converging on a single aligned state]] +- [[persistent irreducible disagreement]] +- [[some disagreements are permanently irreducible because they stem from genuine value differences not information gaps and systems must map rather than eliminate them]] + +Topics: +- domains/ai-alignment/_map +- foundations/collective-intelligence/_map +- core/mechanisms/_map \ No newline at end of file diff --git a/domains/ai-alignment/post-arrow-social-choice-mechanisms-work-by-weakening-independence-of-irrelevant-alternatives.md b/domains/ai-alignment/post-arrow-social-choice-mechanisms-work-by-weakening-independence-of-irrelevant-alternatives.md new file mode 100644 index 000000000..9aa9040d2 --- /dev/null +++ b/domains/ai-alignment/post-arrow-social-choice-mechanisms-work-by-weakening-independence-of-irrelevant-alternatives.md @@ -0,0 +1,42 @@ +--- +type: claim +domain: ai-alignment +secondary_domains: [mechanisms, collective-intelligence] +description: "Practical voting methods like Borda Count and Ranked Pairs avoid Arrow's impossibility by sacrificing IIA rather than claiming to overcome the theorem" +confidence: proven +source: "Conitzer et al. (2024), 'Social Choice Should Guide AI Alignment' (ICML 2024)" +created: 2026-03-11 +--- + +# Post-Arrow social choice mechanisms work by weakening independence of irrelevant alternatives + +Arrow's impossibility theorem proves that no ordinal preference aggregation method can simultaneously satisfy unrestricted domain, Pareto efficiency, independence of irrelevant alternatives (IIA), and non-dictatorship. Rather than claiming to overcome this theorem, post-Arrow social choice theory has spent 70 years developing practical mechanisms that work by deliberately weakening IIA. + +Conitzer et al. (2024) emphasize this key insight: "for ordinal preference aggregation, in order to avoid dictatorships, oligarchies and vetoers, one must weaken IIA." Practical voting methods like Borda Count, Instant Runoff Voting, and Ranked Pairs all sacrifice IIA to achieve other desirable properties. This is not a failure—it's a principled tradeoff that enables functional collective decision-making. + +The paper recommends examining specific voting methods that have been formally analyzed for their properties rather than searching for a mythical "perfect" aggregation method that Arrow proved cannot exist. Different methods make different tradeoffs, and the choice should depend on the specific alignment context. + +## Evidence + +- Arrow's impossibility theorem (1951) establishes the fundamental constraint +- Conitzer et al. (2024) explicitly state: "Rather than claiming to overcome Arrow's theorem, the paper leverages post-Arrow social choice theory" +- Specific mechanisms recommended: Borda Count, Instant Runoff, Ranked Pairs—all formally analyzed for their properties +- The paper proposes RLCHF variants that use these established social welfare functions rather than inventing new aggregation methods + +## Practical Implications + +This resolves a common confusion in AI alignment discussions: people often cite Arrow's theorem as proof that preference aggregation is impossible, when the actual lesson is that perfect aggregation is impossible and we must choose which properties to prioritize. The 70-year history of social choice theory provides a menu of well-understood options. + +For AI alignment, this means: (1) stop searching for a universal aggregation method, (2) explicitly choose which Arrow conditions to relax based on the deployment context, (3) use established voting methods with known properties rather than ad-hoc aggregation. + +--- + +Relevant Notes: +- [[designing coordination rules is categorically different from designing coordination outcomes as nine intellectual traditions independently confirm]] +- [[collective intelligence requires diversity as a structural precondition not a moral preference]] +- [[persistent irreducible disagreement]] + +Topics: +- domains/ai-alignment/_map +- core/mechanisms/_map +- foundations/collective-intelligence/_map \ No newline at end of file diff --git a/domains/ai-alignment/representative-sampling-and-deliberative-mechanisms-should-replace-convenience-platforms-for-ai-alignment-feedback.md b/domains/ai-alignment/representative-sampling-and-deliberative-mechanisms-should-replace-convenience-platforms-for-ai-alignment-feedback.md new file mode 100644 index 000000000..79742e5d8 --- /dev/null +++ b/domains/ai-alignment/representative-sampling-and-deliberative-mechanisms-should-replace-convenience-platforms-for-ai-alignment-feedback.md @@ -0,0 +1,47 @@ +--- +type: claim +domain: ai-alignment +secondary_domains: [mechanisms, collective-intelligence] +description: "AI alignment feedback should use citizens assemblies or representative sampling rather than crowdworker platforms to ensure evaluator diversity reflects actual populations" +confidence: likely +source: "Conitzer et al. (2024), 'Social Choice Should Guide AI Alignment' (ICML 2024)" +created: 2026-03-11 +--- + +# Representative sampling and deliberative mechanisms should replace convenience platforms for AI alignment feedback + +Conitzer et al. (2024) argue that current RLHF implementations use convenience sampling (crowdworker platforms like MTurk) rather than representative sampling or deliberative mechanisms. This creates systematic bias in whose values shape AI behavior. The paper recommends citizens' assemblies or stratified representative sampling as alternatives. + +The core issue: crowdworker platforms systematically over-represent certain demographics (younger, more educated, Western, tech-comfortable) and under-represent others. If AI alignment depends on human feedback, the composition of the feedback pool determines whose values are encoded. Convenience sampling makes this choice implicitly based on who signs up for crowdwork platforms. + +Deliberative mechanisms like citizens' assemblies add a second benefit: evaluators engage with each other's perspectives and reasoning, not just their initial preferences. This can surface shared values that aren't apparent from aggregating isolated individual judgments. + +## Evidence + +- Conitzer et al. (2024) explicitly recommend "representative sampling or deliberative mechanisms (citizens' assemblies) rather than convenience platforms" +- The paper cites [[democratic alignment assemblies produce constitutions as effective as expert-designed ones while better representing diverse populations]] as evidence that deliberative approaches work +- Current RLHF implementations predominantly use MTurk, Upwork, or similar platforms + +## Practical Challenges + +Representative sampling and deliberative mechanisms are more expensive and slower than crowdworker platforms. This creates competitive pressure: companies that use convenience sampling can iterate faster and cheaper than those using representative sampling. The paper doesn't address how to resolve this tension. + +Additionally: representative of what population? Global? National? Users of the specific AI system? Different choices lead to different value distributions. + +## Relationship to Existing Work + +This recommendation directly supports [[collective intelligence requires diversity as a structural precondition not a moral preference]]—diversity isn't just normatively desirable, it's necessary for the aggregation mechanism to work correctly. + +The deliberative component connects to [[democratic alignment assemblies produce constitutions as effective as expert-designed ones while better representing diverse populations]], which provides empirical evidence that deliberation improves alignment outcomes. + +--- + +Relevant Notes: +- [[collective intelligence requires diversity as a structural precondition not a moral preference]] +- [[democratic alignment assemblies produce constitutions as effective as expert-designed ones while better representing diverse populations]] +- [[community-centred norm elicitation surfaces alignment targets materially different from developer-specified rules]] + +Topics: +- domains/ai-alignment/_map +- core/mechanisms/_map +- foundations/collective-intelligence/_map \ No newline at end of file diff --git a/domains/ai-alignment/rlchf-aggregated-rankings-variant-combines-evaluator-rankings-via-social-welfare-function-before-reward-model-training.md b/domains/ai-alignment/rlchf-aggregated-rankings-variant-combines-evaluator-rankings-via-social-welfare-function-before-reward-model-training.md new file mode 100644 index 000000000..7f13ac1db --- /dev/null +++ b/domains/ai-alignment/rlchf-aggregated-rankings-variant-combines-evaluator-rankings-via-social-welfare-function-before-reward-model-training.md @@ -0,0 +1,49 @@ +--- +type: claim +domain: ai-alignment +secondary_domains: [mechanisms] +description: "The aggregated rankings variant of RLCHF applies formal social choice functions to combine multiple evaluator rankings before training the reward model" +confidence: experimental +source: "Conitzer et al. (2024), 'Social Choice Should Guide AI Alignment' (ICML 2024)" +created: 2026-03-11 +--- + +# RLCHF aggregated rankings variant combines evaluator rankings via social welfare function before reward model training + +Conitzer et al. (2024) propose Reinforcement Learning from Collective Human Feedback (RLCHF) as a formalization of preference aggregation in AI alignment. The aggregated rankings variant works by: (1) collecting rankings of AI responses from multiple evaluators, (2) combining these rankings using a formal social welfare function (e.g., Borda Count, Ranked Pairs), (3) training the reward model on the aggregated ranking rather than individual preferences. + +This approach makes the social choice decision explicit and auditable. Instead of implicitly aggregating through dataset composition or reward model averaging, the aggregation happens at the ranking level using well-studied voting methods with known properties. + +The key architectural choice: aggregation happens before reward model training, not during or after. This means the reward model learns from a collective preference signal rather than trying to learn individual preferences and aggregate them internally. + +## Evidence + +- Conitzer et al. (2024) describe two RLCHF variants; this is the first +- The paper recommends specific social welfare functions: Borda Count, Instant Runoff, Ranked Pairs +- This approach connects to 70+ years of social choice theory on voting methods + +## Comparison to Standard RLHF + +Standard RLHF typically aggregates preferences implicitly through: +- Dataset composition (which evaluators are included) +- Majority voting on pairwise comparisons +- Averaging reward model predictions + +RLCHF makes this aggregation explicit and allows practitioners to choose aggregation methods based on their normative properties rather than computational convenience. + +## Relationship to Existing Work + +This mechanism directly addresses the failure mode identified in [[RLHF and DPO both fail at preference diversity because they assume a single reward function can capture context-dependent human values]]. By aggregating at the ranking level with formal social choice functions, RLCHF preserves more information about preference diversity than collapsing to a single reward function. + +The approach also connects to [[modeling preference sensitivity as a learned distribution rather than a fixed scalar resolves DPO diversity failures without demographic labels or explicit user modeling]]—both are attempts to handle preference heterogeneity more formally. + +--- + +Relevant Notes: +- [[RLHF and DPO both fail at preference diversity because they assume a single reward function can capture context-dependent human values]] +- [[modeling preference sensitivity as a learned distribution rather than a fixed scalar resolves DPO diversity failures without demographic labels or explicit user modeling]] +- [[post-arrow-social-choice-mechanisms-work-by-weakening-independence-of-irrelevant-alternatives]] + +Topics: +- domains/ai-alignment/_map +- core/mechanisms/_map \ No newline at end of file diff --git a/domains/ai-alignment/rlchf-features-based-variant-models-individual-preferences-with-evaluator-characteristics-enabling-aggregation-across-diverse-groups.md b/domains/ai-alignment/rlchf-features-based-variant-models-individual-preferences-with-evaluator-characteristics-enabling-aggregation-across-diverse-groups.md new file mode 100644 index 000000000..c6b1ad63b --- /dev/null +++ b/domains/ai-alignment/rlchf-features-based-variant-models-individual-preferences-with-evaluator-characteristics-enabling-aggregation-across-diverse-groups.md @@ -0,0 +1,50 @@ +--- +type: claim +domain: ai-alignment +secondary_domains: [mechanisms] +description: "The features-based RLCHF variant learns individual preference models that incorporate evaluator characteristics allowing aggregation across demographic or value-based groups" +confidence: experimental +source: "Conitzer et al. (2024), 'Social Choice Should Guide AI Alignment' (ICML 2024)" +created: 2026-03-11 +--- + +# RLCHF features-based variant models individual preferences with evaluator characteristics enabling aggregation across diverse groups + +The second RLCHF variant proposed by Conitzer et al. (2024) takes a different approach: instead of aggregating rankings directly, it builds individual preference models that incorporate evaluator characteristics (demographics, values, context). These models can then be aggregated across groups, enabling context-sensitive preference aggregation. + +This approach allows the system to learn: "People with characteristic X tend to prefer response type Y in context Z." Aggregation then happens by weighting or combining these learned preference functions according to a social choice rule, rather than aggregating raw rankings. + +The key advantage: this variant can handle preference heterogeneity more flexibly than the aggregated rankings variant. It can adapt aggregation based on context, represent minority preferences explicitly, and enable "what would group X prefer?" queries. + +## Evidence + +- Conitzer et al. (2024) describe this as the second RLCHF variant +- The paper notes this approach "incorporates evaluator characteristics" and enables "aggregation across diverse groups" +- This connects to the broader literature on personalized and pluralistic AI systems + +## Comparison to Aggregated Rankings Variant + +Where the aggregated rankings variant collapses preferences into a single collective ranking before training, the features-based variant preserves preference structure throughout. This allows: +- Context-dependent aggregation (different social choice rules for different situations) +- Explicit representation of minority preferences +- Transparency about which groups prefer which responses + +The tradeoff: higher complexity and potential for misuse (e.g., demographic profiling, value discrimination). + +## Relationship to Existing Work + +This approach is conceptually similar to [[modeling preference sensitivity as a learned distribution rather than a fixed scalar resolves DPO diversity failures without demographic labels or explicit user modeling]], but more explicit about incorporating evaluator features. Both recognize that preference heterogeneity is structural, not noise. + +The features-based variant also connects to [[community-centred norm elicitation surfaces alignment targets materially different from developer-specified rules]]—both emphasize that different communities have different legitimate preferences that should be represented rather than averaged away. + +--- + +Relevant Notes: +- [[modeling preference sensitivity as a learned distribution rather than a fixed scalar resolves DPO diversity failures without demographic labels or explicit user modeling]] +- [[community-centred norm elicitation surfaces alignment targets materially different from developer-specified rules]] +- [[RLHF and DPO both fail at preference diversity because they assume a single reward function can capture context-dependent human values]] + +Topics: +- domains/ai-alignment/_map +- core/mechanisms/_map +- foundations/collective-intelligence/_map \ No newline at end of file diff --git a/domains/ai-alignment/rlhf-is-implicit-social-choice-without-normative-scrutiny.md b/domains/ai-alignment/rlhf-is-implicit-social-choice-without-normative-scrutiny.md new file mode 100644 index 000000000..d8d679b81 --- /dev/null +++ b/domains/ai-alignment/rlhf-is-implicit-social-choice-without-normative-scrutiny.md @@ -0,0 +1,40 @@ +--- +type: claim +domain: ai-alignment +description: "Current RLHF implementations make social choice decisions about evaluator selection and preference aggregation without examining their normative properties" +confidence: likely +source: "Conitzer et al. (2024), 'Social Choice Should Guide AI Alignment' (ICML 2024)" +created: 2026-03-11 +--- + +# RLHF is implicit social choice without normative scrutiny + +Reinforcement Learning from Human Feedback (RLHF) necessarily makes social choice decisions—which humans provide input, what feedback is collected, how it's aggregated, and how it's used—but current implementations make these choices without examining their normative properties or drawing on 70+ years of social choice theory. + +Conitzer et al. (2024) argue that RLHF practitioners implicitly answer fundamental social choice questions: Who gets to evaluate? How are conflicting preferences weighted? What aggregation method combines diverse judgments? These decisions have profound implications for whose values shape AI behavior, yet they're typically made based on convenience (e.g., using readily available crowdworker platforms) rather than principled normative reasoning. + +The paper demonstrates that post-Arrow social choice theory has developed practical mechanisms that work within Arrow's impossibility constraints. RLHF essentially reinvented preference aggregation badly, ignoring decades of formal work on voting methods, welfare functions, and pluralistic decision-making. + +## Evidence + +- Conitzer et al. (2024) position paper at ICML 2024, co-authored by Stuart Russell (Berkeley CHAI) and leading social choice theorists +- Current RLHF uses convenience sampling (crowdworker platforms) rather than representative sampling or deliberative mechanisms +- The paper proposes RLCHF (Reinforcement Learning from Collective Human Feedback) as the formal alternative that makes social choice decisions explicit + +## Relationship to Existing Work + +This claim directly addresses the mechanism gap identified in [[RLHF and DPO both fail at preference diversity because they assume a single reward function can capture context-dependent human values]]. Where that claim focuses on the technical failure mode (single reward function), this claim identifies the root cause: RLHF makes social choice decisions without social choice theory. + +The paper's proposed solution—RLCHF with explicit social welfare functions—connects to [[collective intelligence requires diversity as a structural precondition not a moral preference]] by formalizing how diverse evaluator input should be preserved rather than collapsed. + +--- + +Relevant Notes: +- [[RLHF and DPO both fail at preference diversity because they assume a single reward function can capture context-dependent human values]] +- [[collective intelligence requires diversity as a structural precondition not a moral preference]] +- [[AI alignment is a coordination problem not a technical problem]] + +Topics: +- domains/ai-alignment/_map +- core/mechanisms/_map +- foundations/collective-intelligence/_map \ No newline at end of file diff --git a/domains/internet-finance/aimd-converges-to-fair-resource-allocation-without-global-coordination-through-local-congestion-signals.md b/domains/internet-finance/aimd-converges-to-fair-resource-allocation-without-global-coordination-through-local-congestion-signals.md new file mode 100644 index 000000000..9a2dd05b2 --- /dev/null +++ b/domains/internet-finance/aimd-converges-to-fair-resource-allocation-without-global-coordination-through-local-congestion-signals.md @@ -0,0 +1,37 @@ +--- +type: claim +domain: internet-finance +description: "AIMD algorithm achieves provably fair and stable distributed resource allocation using only local congestion feedback" +confidence: proven +source: "Corless, King, Shorten, Wirth (SIAM 2016) - AIMD Dynamics and Distributed Resource Allocation" +created: 2026-03-11 +secondary_domains: [mechanisms, collective-intelligence] +--- + +# AIMD converges to fair resource allocation without global coordination through local congestion signals + +Additive Increase Multiplicative Decrease (AIMD) is a distributed resource allocation algorithm that provably converges to fair and stable resource sharing among competing agents without requiring centralized control or global information. The algorithm operates through two simple rules: when no congestion is detected, increase resource usage additively (rate += α); when congestion is detected, decrease resource usage multiplicatively (rate *= β, where 0 < β < 1). + +The SIAM monograph by Corless et al. demonstrates that AIMD is mathematically guaranteed to converge to equal sharing of available capacity regardless of the number of agents or parameter values. Each agent only needs to observe local congestion signals—no knowledge of other agents, total capacity, or system-wide state is required. This makes AIMD the most widely deployed distributed resource allocation mechanism, originally developed for TCP congestion control and now applicable to smart grid energy allocation, distributed computing, and other domains where multiple agents compete for shared resources. + +The key insight is that AIMD doesn't require predicting load, modeling arrivals, or solving optimization problems. It reacts to observed system state through simple local rules and is guaranteed to find the fair allocation through the dynamics of the algorithm itself. The multiplicative decrease creates faster convergence than purely additive approaches, while the additive increase ensures fairness rather than proportional allocation. + +## Evidence + +- Corless, King, Shorten, Wirth (2016) provide mathematical proofs of convergence and fairness properties +- AIMD is the foundation of TCP congestion control, the most widely deployed distributed algorithm in existence +- The algorithm works across heterogeneous domains: internet bandwidth, energy grids, computing resources +- Convergence is guaranteed regardless of number of competing agents or their parameter choices + +--- + +Relevant Notes: +- [[coordination mechanisms]] +- [[optimal governance requires mixing mechanisms because different decisions have different manipulation risk profiles]] +- [[collective intelligence requires diversity as a structural precondition not a moral preference]] +- [[designing coordination rules is categorically different from designing coordination outcomes as nine intellectual traditions independently confirm]] + +Topics: +- domains/internet-finance/_map +- core/mechanisms/_map +- foundations/collective-intelligence/_map \ No newline at end of file diff --git a/domains/internet-finance/aimd-scaling-solves-variable-load-expensive-compute-coordination-without-prediction.md b/domains/internet-finance/aimd-scaling-solves-variable-load-expensive-compute-coordination-without-prediction.md new file mode 100644 index 000000000..18938df73 --- /dev/null +++ b/domains/internet-finance/aimd-scaling-solves-variable-load-expensive-compute-coordination-without-prediction.md @@ -0,0 +1,46 @@ +--- +type: claim +domain: internet-finance +description: "AIMD provides principled autoscaling for systems with expensive compute and variable load by reacting to queue state rather than forecasting demand" +confidence: experimental +source: "Corless et al. (SIAM 2016) applied to Teleo pipeline architecture" +created: 2026-03-11 +secondary_domains: [mechanisms, critical-systems] +--- + +# AIMD scaling solves variable-load expensive-compute coordination without prediction + +For systems with expensive computational operations and highly variable load—such as AI evaluation pipelines where extraction is cheap but evaluation is costly—AIMD provides a principled scaling algorithm that doesn't require demand forecasting or optimization modeling. The algorithm operates by observing queue state: when the evaluation queue is shrinking (no congestion), increase extraction workers by 1 per cycle; when the queue is growing (congestion detected), halve extraction workers. + +This approach is particularly well-suited to scenarios where: +1. Downstream operations (evaluation) are significantly more expensive than upstream operations (extraction) +2. Load is unpredictable and varies substantially over time +3. The cost of overprovisioning is high (wasted expensive compute) +4. The cost of underprovisioning is manageable (slightly longer queue wait times) + +The AIMD dynamics guarantee convergence to a stable operating point where extraction rate matches evaluation capacity, without requiring any prediction of future load, modeling of arrival patterns, or solution of optimization problems. The system self-regulates through observed congestion signals (queue growth/shrinkage) and simple local rules. + +The multiplicative decrease (halving workers on congestion) provides rapid response to capacity constraints, while the additive increase (adding one worker when uncongested) provides gradual scaling that avoids overshooting. This asymmetry is critical: it's better to scale down too aggressively and scale up conservatively than vice versa when downstream compute is expensive. + +## Evidence + +- Corless et al. (2016) prove AIMD convergence properties hold for general resource allocation problems beyond network bandwidth +- The Teleo pipeline architecture exhibits the exact characteristics AIMD is designed for: cheap extraction, expensive evaluation, variable load +- AIMD's "no prediction required" property eliminates the complexity and fragility of load forecasting models +- The algorithm's proven stability guarantees mean it won't oscillate or diverge regardless of load patterns + +## Challenges + +This is an application of proven AIMD theory to a specific system architecture, but the actual performance in the Teleo pipeline context is untested. The claim that AIMD is "perfect for" this setting is theoretical—empirical validation would strengthen confidence from experimental to likely. + +--- + +Relevant Notes: +- [[aimd-converges-to-fair-resource-allocation-without-global-coordination-through-local-congestion-signals]] +- [[coordination mechanisms]] +- [[designing coordination rules is categorically different from designing coordination outcomes as nine intellectual traditions independently confirm]] + +Topics: +- domains/internet-finance/_map +- core/mechanisms/_map +- foundations/critical-systems/_map \ No newline at end of file diff --git a/domains/internet-finance/moderate-scale-queueing-systems-benefit-from-simple-threshold-policies-over-sophisticated-algorithms-because-square-root-staffing-captures-most-efficiency-gains.md b/domains/internet-finance/moderate-scale-queueing-systems-benefit-from-simple-threshold-policies-over-sophisticated-algorithms-because-square-root-staffing-captures-most-efficiency-gains.md new file mode 100644 index 000000000..508ca66bc --- /dev/null +++ b/domains/internet-finance/moderate-scale-queueing-systems-benefit-from-simple-threshold-policies-over-sophisticated-algorithms-because-square-root-staffing-captures-most-efficiency-gains.md @@ -0,0 +1,37 @@ +--- +type: claim +domain: internet-finance +description: "At 5-20 server scale, queueing theory threshold policies capture most benefit without algorithmic complexity" +confidence: likely +source: "van Leeuwaarden, Mathijsen, Sanders (SIAM Review 2018) - empirical validation of square-root staffing at moderate scale" +created: 2026-03-11 +depends_on: ["square-root-staffing-principle-achieves-economies-of-scale-in-queueing-systems-by-operating-near-full-utilization-with-manageable-delays.md"] +--- + +# Moderate-scale queueing systems benefit from simple threshold policies over sophisticated algorithms because square-root staffing captures most efficiency gains + +For systems operating at moderate scale (5-20 servers), the mathematical properties of the Halfin-Whitt regime mean that simple threshold-based policies informed by queueing theory capture most of the available efficiency gains. Sophisticated dynamic algorithms add implementation complexity without proportional benefit at this scale. + +The square-root staffing principle works empirically even for systems as small as 5-6 servers, which means the core economies-of-scale insight applies well below the asymptotic regime where the mathematical proofs strictly hold. This has direct implications for pipeline architecture: a system with 5-6 workers doesn't need complex autoscaling algorithms or machine learning-based load prediction. + +## Evidence + +The SIAM Review tutorial explicitly notes that "square-root safety staffing works empirically even for moderate-sized systems (5-20 servers)" and that "at our scale (5-6 workers), we're in the 'moderate system' range where square-root staffing still provides useful guidance." + +The key takeaway from the tutorial: "we don't need sophisticated algorithms for a system this small. Simple threshold policies informed by queueing theory will capture most of the benefit." + +## Practical Application + +For Teleo pipeline architecture operating at 5-6 workers, this means: +- Simple threshold-based autoscaling policies are sufficient +- Complex predictive algorithms add cost without proportional benefit +- The mathematical foundation (Halfin-Whitt regime) validates simple approaches at this scale + +--- + +Relevant Notes: +- [[square-root-staffing-principle-achieves-economies-of-scale-in-queueing-systems-by-operating-near-full-utilization-with-manageable-delays]] +- domains/internet-finance/_map + +Topics: +- core/mechanisms/_map diff --git a/domains/internet-finance/square-root-staffing-formula-requires-peakedness-adjustment-for-non-poisson-arrivals.md b/domains/internet-finance/square-root-staffing-formula-requires-peakedness-adjustment-for-non-poisson-arrivals.md new file mode 100644 index 000000000..022959ee0 --- /dev/null +++ b/domains/internet-finance/square-root-staffing-formula-requires-peakedness-adjustment-for-non-poisson-arrivals.md @@ -0,0 +1,36 @@ +--- +type: claim +domain: internet-finance +description: "Bursty arrival processes require more safety capacity than Poisson models predict, scaled by variance-to-mean ratio" +confidence: proven +source: "Whitt et al., 'Staffing a Service System with Non-Poisson Non-Stationary Arrivals', Cambridge Core, 2016" +created: 2026-03-11 +--- + +# Square-root staffing formula requires peakedness adjustment for non-Poisson arrivals because bursty processes need proportionally more safety capacity than the Poisson baseline predicts + +The standard square-root staffing formula (workers = mean load + safety factor × √mean) assumes Poisson arrivals where variance equals mean. Real-world arrival processes violate this assumption through burstiness (arrivals clustered in time) or smoothness (arrivals more evenly distributed than random). + +Whitt et al. extend the square-root staffing rule by introducing **peakedness** — the variance-to-mean ratio of the arrival process — as the key adjustment parameter. For bursty arrivals (peakedness > 1), systems require MORE safety capacity than Poisson models suggest. For smooth arrivals (peakedness < 1), systems need LESS. + +The modified staffing formula adjusts the square-root safety margin by multiplying by the square root of peakedness. This correction is critical for non-stationary systems where arrival rates vary over time (daily cycles, seasonal patterns, or event-driven spikes). + +## Evidence + +- Whitt et al. (2016) prove that peakedness — the variance-to-mean ratio — captures the essential non-Poisson behavior for staffing calculations +- Standard Poisson assumption (variance = mean) fails empirically for bursty workloads like research paper dumps, product launches, or customer service spikes +- Using constant staffing (fixed MAX_WORKERS) regardless of queue state creates dual failure: over-provisioning during quiet periods (wasted compute) and under-provisioning during bursts (queue explosion) + +## Relevance to Pipeline Architecture + +Teleo's research pipeline exhibits textbook non-Poisson non-stationary arrivals: research dumps arrive in bursts of 15+ sources, futardio launches come in waves of 20+ proposals, while other days see minimal activity. The peakedness parameter quantifies exactly how much extra capacity is needed beyond naive square-root staffing. + +This directly informs dynamic worker scaling: measure empirical peakedness from historical arrival data, adjust safety capacity accordingly, and scale workers based on current queue depth rather than using fixed limits. + +--- + +Relevant Notes: +- domains/internet-finance/_map + +Topics: +- core/mechanisms/_map diff --git a/domains/internet-finance/square-root-staffing-principle-achieves-economies-of-scale-in-queueing-systems-by-operating-near-full-utilization-with-manageable-delays.md b/domains/internet-finance/square-root-staffing-principle-achieves-economies-of-scale-in-queueing-systems-by-operating-near-full-utilization-with-manageable-delays.md new file mode 100644 index 000000000..e4465c145 --- /dev/null +++ b/domains/internet-finance/square-root-staffing-principle-achieves-economies-of-scale-in-queueing-systems-by-operating-near-full-utilization-with-manageable-delays.md @@ -0,0 +1,35 @@ +--- +type: claim +domain: internet-finance +description: "The QED Halfin-Whitt regime shows server count n grows while utilization approaches 1 at rate Θ(1/√n)" +confidence: proven +source: "van Leeuwaarden, Mathijsen, Sanders (SIAM Review 2018) - Economies-of-Scale in Many-Server Queueing Systems" +created: 2026-03-11 +--- + +# Square-root staffing principle achieves economies of scale in queueing systems by operating near full utilization with manageable delays + +The QED (Quality-and-Efficiency-Driven) Halfin-Whitt heavy-traffic regime provides the mathematical foundation for understanding economies of scale in multi-server systems. As server count n grows, the system can operate at utilization approaching 1 while maintaining bounded delays, with the key insight that excess capacity needs to grow only at rate Θ(1/√n) rather than linearly. + +This "square root staffing" principle means larger systems need proportionally fewer excess servers for the same service quality. A system with 100 servers might need 10 excess servers for target service levels, while a system with 400 servers needs only 20 excess servers (not 40) for the same quality. + +The regime applies across system sizes from tens to thousands of servers, and empirical validation shows the square-root safety staffing works even for moderate-sized systems in the 5-20 server range. + +## Evidence + +From the SIAM Review tutorial: +- Mathematical proof that utilization approaches 1 at rate Θ(1/√n) as server count grows +- Empirical validation showing square-root staffing works for systems as small as 5-20 servers +- The regime connects abstract queueing theory to practical staffing decisions across industries + +## Implications for Pipeline Architecture + +For systems in the 5-6 worker range, sophisticated dynamic algorithms provide minimal benefit over simple threshold policies informed by queueing theory. The economies-of-scale result also indicates that marginal value per worker decreases as systems grow beyond 20+ workers, which is critical for cost optimization in scaled deployments. + +--- + +Relevant Notes: +- domains/internet-finance/_map + +Topics: +- core/mechanisms/_map diff --git a/domains/internet-finance/time-varying-arrival-rates-require-dynamic-staffing-not-constant-max-workers.md b/domains/internet-finance/time-varying-arrival-rates-require-dynamic-staffing-not-constant-max-workers.md new file mode 100644 index 000000000..6cc1d9569 --- /dev/null +++ b/domains/internet-finance/time-varying-arrival-rates-require-dynamic-staffing-not-constant-max-workers.md @@ -0,0 +1,42 @@ +--- +type: claim +domain: internet-finance +description: "Replacing non-stationary arrival rates with constant staffing leads to systematic over- or under-provisioning" +confidence: proven +source: "Whitt et al., 'Staffing a Service System with Non-Poisson Non-Stationary Arrivals', Cambridge Core, 2016" +created: 2026-03-11 +--- + +# Time-varying arrival rates require dynamic staffing not constant MAX_WORKERS because using average or maximum rates as constants creates systematic misallocation across the arrival cycle + +Non-stationary arrival processes — where the arrival rate itself changes over time — cannot be efficiently staffed with constant worker counts. Whitt et al. demonstrate that replacing time-varying rates with either the average rate or the maximum rate produces badly mis-staffed systems: + +- **Constant = average rate**: Under-staffed during peak periods, leading to queue explosions and service degradation +- **Constant = maximum rate**: Over-staffed during off-peak periods, wasting capacity and compute resources + +The optimal approach tracks the arrival rate over time and adjusts staffing dynamically to match the current load plus an appropriate safety margin (scaled by peakedness for non-Poisson processes). + +## Evidence + +- Whitt et al. (2016) prove that time-varying arrival rates require time-varying staffing levels for efficiency +- Constant staffing at maximum capacity wastes resources during low-traffic periods +- Constant staffing at average capacity fails catastrophically during burst periods +- Dynamic staffing based on current queue state and arrival rate estimates achieves both efficiency (no waste during quiet periods) and reliability (adequate capacity during bursts) + +## Application to Teleo Pipeline + +Teleo's research processing pipeline exhibits strong non-stationarity: research dumps and futardio launches create burst periods with 15-20+ simultaneous arrivals, while other periods see minimal activity. Using a fixed MAX_WORKERS setting (constant staffing) is the worst of both worlds: + +- During bursts: MAX_WORKERS is too low, queue explodes, processing stalls +- During quiet periods: MAX_WORKERS is too high, workers sit idle, compute wasted + +Dynamic worker scaling based on current queue depth and estimated arrival rate (with peakedness adjustment) is the theoretically correct solution. + +--- + +Relevant Notes: +- [[square-root-staffing-formula-requires-peakedness-adjustment-for-non-poisson-arrivals]] +- domains/internet-finance/_map + +Topics: +- core/mechanisms/_map diff --git a/inbox/archive/.extraction-debug/2024-08-28-futardio-proposal-proposal-7.json b/inbox/archive/.extraction-debug/2024-08-28-futardio-proposal-proposal-7.json new file mode 100644 index 000000000..29c04d610 --- /dev/null +++ b/inbox/archive/.extraction-debug/2024-08-28-futardio-proposal-proposal-7.json @@ -0,0 +1,62 @@ +{ + "raw_response": "```json\n{\n \"claims\": [],\n \"enrichments\": [],\n \"entities\": [\n {\n \"filename\": \"metadao-proposal-7.md\",\n \"domain\": \"internet-finance\",\n \"action\": \"create\",\n \"entity_type\": \"decision_market\",\n \"content\": \"---\\ntype: entity\\nentity_type: decision_market\\nname: \\\"MetaDAO: Proposal #7\\\"\\ndomain: internet-finance\\nstatus: failed\\nparent_entity: \\\"[[metadao]]\\\"\\nplatform: \\\"futardio\\\"\\nproposer: \\\"HwBL75xHHKcXSMNcctq3UqWaEJPDWVQz6NazZJNjWaQc\\\"\\nproposal_url: \\\"https://www.futard.io/proposal/AuNNyR4oU2zkG1sYBzJ3DJmyDzMKSmSW2yASorWenuC6\\\"\\nproposal_date: 2024-08-28\\nresolution_date: 2024-09-01\\ncategory: \\\"unknown\\\"\\nsummary: \\\"MetaDAO Proposal #7 failed after 4-day voting period with no proposal text or market data available\\\"\\ntracked_by: rio\\ncreated: 2026-03-11\\n---\\n\\n# MetaDAO: Proposal #7\\n\\n## Summary\\nProposal #7 on MetaDAO was created on 2024-08-28 and failed on 2024-09-01. No proposal text, rationale, or market data is available in the source archive. The proposal ran on Autocrat version 0.3.\\n\\n## Market Data\\n- **Outcome:** Failed\\n- **Proposer:** HwBL75xHHKcXSMNcctq3UqWaEJPDWVQz6NazZJNjWaQc\\n- **Duration:** 4 days (2024-08-28 to 2024-09-01)\\n- **Platform:** Futardio\\n- **Autocrat Version:** 0.3\\n\\n## Significance\\nThis proposal represents an archival record of a failed MetaDAO governance decision. Without proposal content or market volume data, it serves primarily as a timeline marker in MetaDAO's governance history during the Autocrat v0.3 era.\\n\\n## Relationship to KB\\n- [[metadao]] - governance decision\\n- [[futardio]] - platform used\\n\",\n \"timeline_entry\": \"- **2024-08-28** \u2014 [[metadao-proposal-7]] failed: Proposal #7 rejected after 4-day voting period (no details available)\"\n }\n ],\n \"source_update\": {\n \"status\": \"processed\",\n \"processed_by\": \"rio\",\n \"processed_date\": \"2026-03-11\",\n \"claims_extracted\": [],\n \"enrichments_applied\": [],\n \"entities_updated\": [\"metadao-proposal-7.md\", \"metadao.md\"],\n \"key_facts\": [\n \"MetaDAO Proposal #7 created 2024-08-28, failed 2024-09-01\",\n \"Proposal account: AuNNyR4oU2zkG1sYBzJ3DJmyDzMKSmSW2yASorWenuC6\",\n \"DAO account: GWywkp2mY2vzAaLydR2MBXRCqk2vBTyvtVRioujxi5Ce\",\n \"Proposer: HwBL75xHHKcXSMNcctq3UqWaEJPDWVQz6NazZJNjWaQc\",\n \"Autocrat version: 0.3\"\n ],\n \"notes\": \"Source contains only metadata about a failed MetaDAO proposal with no proposal text, rationale, market data, or voting details. Created decision_market entity for archival completeness and timeline tracking. No extractable claims or enrichments due to absence of substantive content about mechanisms, outcomes, or governance dynamics. This is purely structural metadata documenting that a proposal existed and failed.\"\n }\n}\n```", + "parsed": { + "claims": [], + "enrichments": [], + "entities": [ + { + "filename": "metadao-proposal-7.md", + "domain": "internet-finance", + "action": "create", + "entity_type": "decision_market", + "content": "---\ntype: entity\nentity_type: decision_market\nname: \"MetaDAO: Proposal #7\"\ndomain: internet-finance\nstatus: failed\nparent_entity: \"[[metadao]]\"\nplatform: \"futardio\"\nproposer: \"HwBL75xHHKcXSMNcctq3UqWaEJPDWVQz6NazZJNjWaQc\"\nproposal_url: \"https://www.futard.io/proposal/AuNNyR4oU2zkG1sYBzJ3DJmyDzMKSmSW2yASorWenuC6\"\nproposal_date: 2024-08-28\nresolution_date: 2024-09-01\ncategory: \"unknown\"\nsummary: \"MetaDAO Proposal #7 failed after 4-day voting period with no proposal text or market data available\"\ntracked_by: rio\ncreated: 2026-03-11\n---\n\n# MetaDAO: Proposal #7\n\n## Summary\nProposal #7 on MetaDAO was created on 2024-08-28 and failed on 2024-09-01. No proposal text, rationale, or market data is available in the source archive. The proposal ran on Autocrat version 0.3.\n\n## Market Data\n- **Outcome:** Failed\n- **Proposer:** HwBL75xHHKcXSMNcctq3UqWaEJPDWVQz6NazZJNjWaQc\n- **Duration:** 4 days (2024-08-28 to 2024-09-01)\n- **Platform:** Futardio\n- **Autocrat Version:** 0.3\n\n## Significance\nThis proposal represents an archival record of a failed MetaDAO governance decision. Without proposal content or market volume data, it serves primarily as a timeline marker in MetaDAO's governance history during the Autocrat v0.3 era.\n\n## Relationship to KB\n- [[metadao]] - governance decision\n- [[futardio]] - platform used\n", + "timeline_entry": "- **2024-08-28** \u2014 [[metadao-proposal-7]] failed: Proposal #7 rejected after 4-day voting period (no details available)" + } + ], + "source_update": { + "status": "null-result", + "processed_by": "rio", + "processed_date": "2026-03-11", + "claims_extracted": [], + "enrichments_applied": [], + "entities_updated": [ + "metadao-proposal-7.md", + "metadao.md" + ], + "key_facts": [ + "MetaDAO Proposal #7 created 2024-08-28, failed 2024-09-01", + "Proposal account: AuNNyR4oU2zkG1sYBzJ3DJmyDzMKSmSW2yASorWenuC6", + "DAO account: GWywkp2mY2vzAaLydR2MBXRCqk2vBTyvtVRioujxi5Ce", + "Proposer: HwBL75xHHKcXSMNcctq3UqWaEJPDWVQz6NazZJNjWaQc", + "Autocrat version: 0.3" + ], + "notes": "Source contains only metadata about a failed MetaDAO proposal with no proposal text, rationale, market data, or voting details. Created decision_market entity for archival completeness and timeline tracking. No extractable claims or enrichments due to absence of substantive content about mechanisms, outcomes, or governance dynamics. This is purely structural metadata documenting that a proposal existed and failed.", + "model": "anthropic/claude-sonnet-4.5" + } + }, + "model": "anthropic/claude-sonnet-4.5", + "date": "2026-03-15", + "tokens": { + "prompt_tokens": 11434, + "completion_tokens": 1052, + "total_tokens": 12486, + "cost": 0.050082, + "is_byok": false, + "prompt_tokens_details": { + "cached_tokens": 0, + "cache_write_tokens": 0, + "audio_tokens": 0, + "video_tokens": 0 + }, + "cost_details": { + "upstream_inference_cost": 0.050082, + "upstream_inference_prompt_cost": 0.034302, + "upstream_inference_completions_cost": 0.01578 + }, + "completion_tokens_details": { + "reasoning_tokens": 0, + "image_tokens": 0, + "audio_tokens": 0 + } + } +} \ No newline at end of file diff --git a/inbox/archive/.extraction-debug/2024-11-13-futardio-proposal-cut-emissions-by-50.json b/inbox/archive/.extraction-debug/2024-11-13-futardio-proposal-cut-emissions-by-50.json new file mode 100644 index 000000000..85e341512 --- /dev/null +++ b/inbox/archive/.extraction-debug/2024-11-13-futardio-proposal-cut-emissions-by-50.json @@ -0,0 +1,67 @@ +{ + "raw_response": "```json\n{\n \"claims\": [],\n \"enrichments\": [],\n \"entities\": [\n {\n \"filename\": \"coal-cut-emissions-by-50.md\",\n \"domain\": \"internet-finance\",\n \"action\": \"create\",\n \"entity_type\": \"decision_market\",\n \"content\": \"---\\ntype: entity\\nentity_type: decision_market\\nname: \\\"Coal: Cut emissions by 50%?\\\"\\ndomain: internet-finance\\nstatus: passed\\nparent_entity: \\\"[[coal]]\\\"\\nplatform: \\\"futardio\\\"\\nproposer: \\\"proPaC9tVZEsmgDtNhx15e7nSpoojtPD3H9h4GqSqB2\\\"\\nproposal_url: \\\"https://www.futard.io/proposal/6LcxhHS3JvDtbS1GoQS18EgH5Pzf7AnqQpR7D4HxmWpy\\\"\\nproposal_date: 2024-11-13\\nresolution_date: 2024-11-17\\ncategory: \\\"mechanism\\\"\\nsummary: \\\"Proposal to halve Coal token emission rate from 15.625 to 7.8125 per minute and establish bi-monthly decision markets for future adjustments\\\"\\ntracked_by: rio\\ncreated: 2026-03-11\\n---\\n\\n# Coal: Cut emissions by 50%?\\n\\n## Summary\\nProposal to reduce Coal token emission rate from 15.625 to 7.8125 per minute (from 22,500 to 11,250 per day), effectively halving the target emissions and reducing annual inflation from ~110% to ~56%. The proposal also establishes a framework for bi-monthly decision markets to guide future emission rate adjustments, replacing the original temporary halving schedule.\\n\\n## Market Data\\n- **Outcome:** Passed\\n- **Proposer:** proPaC9tVZEsmgDtNhx15e7nSpoojtPD3H9h4GqSqB2\\n- **Created:** 2024-11-13\\n- **Completed:** 2024-11-17\\n- **Proposal Account:** 6LcxhHS3JvDtbS1GoQS18EgH5Pzf7AnqQpR7D4HxmWpy\\n- **DAO Account:** 3LGGRzLrgwhEbEsNYBSTZc5MLve1bw3nDaHzzfJMQ1PG\\n\\n## Significance\\nThis proposal demonstrates futarchy governance applied to token economics parameters, specifically emission schedules. It replaces a predetermined halving schedule with market-driven decision-making on a recurring basis. The shift from algorithmic to governance-driven emission control represents a test of whether futarchy markets can effectively manage monetary policy parameters that directly affect token holder value.\\n\\nThe proposal also establishes a precedent for regular (bi-monthly) decision markets on core economic parameters, creating a continuous governance feedback loop rather than one-time decisions.\\n\\n## Relationship to KB\\n- [[futardio]] - governance platform\\n- [[MetaDAO]] - parent organization\\n- [[dynamic performance-based token minting replaces fixed emission schedules by tying new token creation to measurable outcomes creating algorithmic meritocracy in token distribution]] - related mechanism pattern\\n\"\n },\n {\n \"filename\": \"coal.md\",\n \"domain\": \"internet-finance\",\n \"action\": \"create\",\n \"entity_type\": \"company\",\n \"content\": \"---\\ntype: entity\\nentity_type: company\\nname: \\\"Coal\\\"\\ndomain: internet-finance\\nstatus: active\\nwebsite: \\\"\\\"\\ntracked_by: rio\\ncreated: 2026-03-11\\nkey_metrics:\\n emission_rate_current: \\\"7.8125 per minute (11,250 per day)\\\"\\n emission_rate_previous: \\\"15.625 per minute (22,500 per day)\\\"\\n inflation_rate_current: \\\"~56% annually\\\"\\n inflation_rate_previous: \\\"~110% annually\\\"\\n circulating_supply_halving_threshold: \\\"7,350,000\\\"\\n halvings_completed: 6\\n---\\n\\n# Coal\\n\\n## Overview\\nCoal is a token project governed through futarchy on the Futardio platform. The project uses decision markets to manage core economic parameters including emission schedules, replacing predetermined algorithmic halvings with market-driven governance decisions on a bi-monthly basis.\\n\\n## Timeline\\n- **2024-11-13** \u2014 [[coal-cut-emissions-by-50]] proposed: halve emission rate from 15.625 to 7.8125 per minute and establish bi-monthly decision markets for future adjustments\\n- **2024-11-17** \u2014 Emission reduction proposal passed, reducing annual inflation from ~110% to ~56%\\n\\n## Relationship to KB\\n- [[futardio]] - governance platform\\n- [[MetaDAO]] - ecosystem\\n- [[dynamic performance-based token minting replaces fixed emission schedules by tying new token creation to measurable outcomes creating algorithmic meritocracy in token distribution]] - related mechanism pattern\\n\"\n }\n ],\n \"source_update\": {\n \"status\": \"processed\",\n \"processed_by\": \"rio\",\n \"processed_date\": \"2026-03-11\",\n \"claims_extracted\": [],\n \"enrichments_applied\": [],\n \"entities_updated\": [\"coal-cut-emissions-by-50.md\", \"coal.md\"],\n \"key_facts\": [\n \"Coal token emission rate reduced from 15.625 to 7.8125 per minute (2024-11-17)\",\n \"Coal annual inflation reduced from ~110% to ~56% (2024-11-17)\",\n \"Coal completed 6 halvings before governance transition\",\n \"Coal proposal 6LcxhHS3JvDtbS1GoQS18EgH5Pzf7AnqQpR7D4HxmWpy passed (2024-11-17)\"\n ],\n \"notes\": \"Source is a futarchy governance proposal for Coal token emission schedule. Extracted as decision_market entity (the proposal itself) and created parent entity for Coal project. No novel claims about futarchy mechanisms - this is a straightforward application of existing governance patterns. The shift from algorithmic to market-driven emission control is notable but represents implementation of known futarchy principles rather than new mechanism insight.\"\n }\n}\n```", + "parsed": { + "claims": [], + "enrichments": [], + "entities": [ + { + "filename": "coal-cut-emissions-by-50.md", + "domain": "internet-finance", + "action": "create", + "entity_type": "decision_market", + "content": "---\ntype: entity\nentity_type: decision_market\nname: \"Coal: Cut emissions by 50%?\"\ndomain: internet-finance\nstatus: passed\nparent_entity: \"[[coal]]\"\nplatform: \"futardio\"\nproposer: \"proPaC9tVZEsmgDtNhx15e7nSpoojtPD3H9h4GqSqB2\"\nproposal_url: \"https://www.futard.io/proposal/6LcxhHS3JvDtbS1GoQS18EgH5Pzf7AnqQpR7D4HxmWpy\"\nproposal_date: 2024-11-13\nresolution_date: 2024-11-17\ncategory: \"mechanism\"\nsummary: \"Proposal to halve Coal token emission rate from 15.625 to 7.8125 per minute and establish bi-monthly decision markets for future adjustments\"\ntracked_by: rio\ncreated: 2026-03-11\n---\n\n# Coal: Cut emissions by 50%?\n\n## Summary\nProposal to reduce Coal token emission rate from 15.625 to 7.8125 per minute (from 22,500 to 11,250 per day), effectively halving the target emissions and reducing annual inflation from ~110% to ~56%. The proposal also establishes a framework for bi-monthly decision markets to guide future emission rate adjustments, replacing the original temporary halving schedule.\n\n## Market Data\n- **Outcome:** Passed\n- **Proposer:** proPaC9tVZEsmgDtNhx15e7nSpoojtPD3H9h4GqSqB2\n- **Created:** 2024-11-13\n- **Completed:** 2024-11-17\n- **Proposal Account:** 6LcxhHS3JvDtbS1GoQS18EgH5Pzf7AnqQpR7D4HxmWpy\n- **DAO Account:** 3LGGRzLrgwhEbEsNYBSTZc5MLve1bw3nDaHzzfJMQ1PG\n\n## Significance\nThis proposal demonstrates futarchy governance applied to token economics parameters, specifically emission schedules. It replaces a predetermined halving schedule with market-driven decision-making on a recurring basis. The shift from algorithmic to governance-driven emission control represents a test of whether futarchy markets can effectively manage monetary policy parameters that directly affect token holder value.\n\nThe proposal also establishes a precedent for regular (bi-monthly) decision markets on core economic parameters, creating a continuous governance feedback loop rather than one-time decisions.\n\n## Relationship to KB\n- [[futardio]] - governance platform\n- [[MetaDAO]] - parent organization\n- [[dynamic performance-based token minting replaces fixed emission schedules by tying new token creation to measurable outcomes creating algorithmic meritocracy in token distribution]] - related mechanism pattern\n" + }, + { + "filename": "coal.md", + "domain": "internet-finance", + "action": "create", + "entity_type": "company", + "content": "---\ntype: entity\nentity_type: company\nname: \"Coal\"\ndomain: internet-finance\nstatus: active\nwebsite: \"\"\ntracked_by: rio\ncreated: 2026-03-11\nkey_metrics:\n emission_rate_current: \"7.8125 per minute (11,250 per day)\"\n emission_rate_previous: \"15.625 per minute (22,500 per day)\"\n inflation_rate_current: \"~56% annually\"\n inflation_rate_previous: \"~110% annually\"\n circulating_supply_halving_threshold: \"7,350,000\"\n halvings_completed: 6\n---\n\n# Coal\n\n## Overview\nCoal is a token project governed through futarchy on the Futardio platform. The project uses decision markets to manage core economic parameters including emission schedules, replacing predetermined algorithmic halvings with market-driven governance decisions on a bi-monthly basis.\n\n## Timeline\n- **2024-11-13** \u2014 [[coal-cut-emissions-by-50]] proposed: halve emission rate from 15.625 to 7.8125 per minute and establish bi-monthly decision markets for future adjustments\n- **2024-11-17** \u2014 Emission reduction proposal passed, reducing annual inflation from ~110% to ~56%\n\n## Relationship to KB\n- [[futardio]] - governance platform\n- [[MetaDAO]] - ecosystem\n- [[dynamic performance-based token minting replaces fixed emission schedules by tying new token creation to measurable outcomes creating algorithmic meritocracy in token distribution]] - related mechanism pattern\n" + } + ], + "source_update": { + "status": "null-result", + "processed_by": "rio", + "processed_date": "2026-03-11", + "claims_extracted": [], + "enrichments_applied": [], + "entities_updated": [ + "coal-cut-emissions-by-50.md", + "coal.md" + ], + "key_facts": [ + "Coal token emission rate reduced from 15.625 to 7.8125 per minute (2024-11-17)", + "Coal annual inflation reduced from ~110% to ~56% (2024-11-17)", + "Coal completed 6 halvings before governance transition", + "Coal proposal 6LcxhHS3JvDtbS1GoQS18EgH5Pzf7AnqQpR7D4HxmWpy passed (2024-11-17)" + ], + "notes": "Source is a futarchy governance proposal for Coal token emission schedule. Extracted as decision_market entity (the proposal itself) and created parent entity for Coal project. No novel claims about futarchy mechanisms - this is a straightforward application of existing governance patterns. The shift from algorithmic to market-driven emission control is notable but represents implementation of known futarchy principles rather than new mechanism insight.", + "model": "anthropic/claude-sonnet-4.5" + } + }, + "model": "anthropic/claude-sonnet-4.5", + "date": "2026-03-15", + "tokens": { + "prompt_tokens": 11561, + "completion_tokens": 1609, + "total_tokens": 13170, + "cost": 0.058818, + "is_byok": false, + "prompt_tokens_details": { + "cached_tokens": 0, + "cache_write_tokens": 0, + "audio_tokens": 0, + "video_tokens": 0 + }, + "cost_details": { + "upstream_inference_cost": 0.058818, + "upstream_inference_prompt_cost": 0.034683, + "upstream_inference_completions_cost": 0.024135 + }, + "completion_tokens_details": { + "reasoning_tokens": 0, + "image_tokens": 0, + "audio_tokens": 0 + } + } +} \ No newline at end of file diff --git a/inbox/archive/2016-00-00-cambridge-staffing-non-poisson-non-stationary-arrivals.md b/inbox/archive/2016-00-00-cambridge-staffing-non-poisson-non-stationary-arrivals.md index c8d5755c9..7663707bc 100644 --- a/inbox/archive/2016-00-00-cambridge-staffing-non-poisson-non-stationary-arrivals.md +++ b/inbox/archive/2016-00-00-cambridge-staffing-non-poisson-non-stationary-arrivals.md @@ -6,8 +6,13 @@ url: https://www.cambridge.org/core/journals/probability-in-the-engineering-and- date: 2016-01-01 domain: internet-finance format: paper -status: unprocessed +status: processed tags: [pipeline-architecture, operations-research, stochastic-modeling, non-stationary-arrivals, capacity-sizing] +processed_by: rio +processed_date: 2026-03-11 +claims_extracted: ["square-root-staffing-formula-requires-peakedness-adjustment-for-non-poisson-arrivals.md", "time-varying-arrival-rates-require-dynamic-staffing-not-constant-max-workers.md"] +extraction_model: "anthropic/claude-sonnet-4.5" +extraction_notes: "Operations research paper on staffing under non-Poisson non-stationary arrivals. Extracted two claims on peakedness adjustment and dynamic staffing requirements. Direct application to Teleo pipeline architecture for worker scaling. No entity data (academic paper, no companies/products/decisions). No enrichments (novel theoretical contribution not covered by existing claims)." --- # Staffing a Service System with Non-Poisson Non-Stationary Arrivals diff --git a/inbox/archive/2016-00-00-corless-aimd-dynamics-distributed-resource-allocation.md b/inbox/archive/2016-00-00-corless-aimd-dynamics-distributed-resource-allocation.md index 14afb40e4..9b4c4df84 100644 --- a/inbox/archive/2016-00-00-corless-aimd-dynamics-distributed-resource-allocation.md +++ b/inbox/archive/2016-00-00-corless-aimd-dynamics-distributed-resource-allocation.md @@ -6,8 +6,13 @@ url: https://epubs.siam.org/doi/book/10.1137/1.9781611974225 date: 2016-01-01 domain: internet-finance format: paper -status: unprocessed +status: processed tags: [pipeline-architecture, operations-research, AIMD, distributed-resource-allocation, congestion-control, fairness] +processed_by: rio +processed_date: 2026-03-11 +claims_extracted: ["aimd-converges-to-fair-resource-allocation-without-global-coordination-through-local-congestion-signals.md", "aimd-scaling-solves-variable-load-expensive-compute-coordination-without-prediction.md"] +extraction_model: "anthropic/claude-sonnet-4.5" +extraction_notes: "Extracted two claims: (1) general AIMD mechanism properties as proven coordination algorithm, (2) specific application to Teleo pipeline architecture. The source is a formal mathematical treatment (SIAM monograph) providing rigorous proofs, making the first claim 'proven' confidence. The second claim is an application proposal with theoretical justification but no empirical validation, hence 'experimental'. No entities to extract—this is pure mechanism theory. No enrichments—AIMD is not currently referenced in the KB." --- # AIMD Dynamics and Distributed Resource Allocation @@ -26,3 +31,10 @@ SIAM monograph on AIMD (Additive Increase Multiplicative Decrease) as a general- ## Relevance to Teleo Pipeline AIMD provides a principled, proven scaling algorithm: when eval queue is shrinking (no congestion), increase extraction workers by 1 per cycle. When eval queue is growing (congestion), halve extraction workers. This doesn't require predicting load, modeling arrivals, or solving optimization problems — it reacts to observed system state and is mathematically guaranteed to converge. Perfect for our "expensive compute, variable load" setting. + + +## Key Facts +- AIMD algorithm: additive increase (rate += α) when no congestion, multiplicative decrease (rate *= β, 0 < β < 1) when congestion detected +- AIMD is the foundation of TCP congestion control +- AIMD has been applied to internet congestion control, smart grid energy allocation, and distributed computing +- AIMD convergence is mathematically proven regardless of number of agents or parameter values diff --git a/inbox/archive/2018-00-00-siam-economies-of-scale-halfin-whitt-regime.md b/inbox/archive/2018-00-00-siam-economies-of-scale-halfin-whitt-regime.md index bed45a506..7f447443f 100644 --- a/inbox/archive/2018-00-00-siam-economies-of-scale-halfin-whitt-regime.md +++ b/inbox/archive/2018-00-00-siam-economies-of-scale-halfin-whitt-regime.md @@ -6,8 +6,13 @@ url: https://epubs.siam.org/doi/10.1137/17M1133944 date: 2018-01-01 domain: internet-finance format: paper -status: unprocessed +status: processed tags: [pipeline-architecture, operations-research, queueing-theory, Halfin-Whitt, economies-of-scale, square-root-staffing] +processed_by: rio +processed_date: 2026-03-11 +claims_extracted: ["square-root-staffing-principle-achieves-economies-of-scale-in-queueing-systems-by-operating-near-full-utilization-with-manageable-delays.md", "moderate-scale-queueing-systems-benefit-from-simple-threshold-policies-over-sophisticated-algorithms-because-square-root-staffing-captures-most-efficiency-gains.md"] +extraction_model: "anthropic/claude-sonnet-4.5" +extraction_notes: "Extracted two claims about queueing theory and economies of scale. The source is a mathematical tutorial with proven results (SIAM Review), so confidence is 'proven' for the core mathematical claim and 'likely' for the practical application claim. No entities to extract (academic paper, no companies/products/decisions). The relevance to Teleo is in pipeline architecture optimization, which is noted in the source's 'Relevance to Teleo Pipeline' section." --- # Economies-of-Scale in Many-Server Queueing Systems @@ -26,3 +31,9 @@ SIAM Review tutorial on the QED (Quality-and-Efficiency-Driven) Halfin-Whitt hea ## Relevance to Teleo Pipeline At our scale (5-6 workers), we're in the "moderate system" range where square-root staffing still provides useful guidance. The key takeaway: we don't need sophisticated algorithms for a system this small. Simple threshold policies informed by queueing theory will capture most of the benefit. The economies-of-scale result also tells us that if we grow to 20+ workers, the marginal value of each additional worker decreases — important for cost optimization. + + +## Key Facts +- Halfin-Whitt QED regime: utilization approaches 1 at rate Θ(1/√n) +- Square-root staffing validated empirically for systems as small as 5-20 servers +- 100-server system needs ~10 excess servers; 400-server system needs ~20 (not 40) for same quality diff --git a/inbox/archive/2024-04-00-conitzer-social-choice-guide-alignment.md b/inbox/archive/2024-04-00-conitzer-social-choice-guide-alignment.md index eb4c1986f..de076d53e 100644 --- a/inbox/archive/2024-04-00-conitzer-social-choice-guide-alignment.md +++ b/inbox/archive/2024-04-00-conitzer-social-choice-guide-alignment.md @@ -7,10 +7,16 @@ date: 2024-04-01 domain: ai-alignment secondary_domains: [mechanisms, collective-intelligence] format: paper -status: unprocessed +status: processed priority: high tags: [social-choice, rlhf, rlchf, evaluator-selection, mechanism-design, pluralism, arrow-workaround] flagged_for_rio: ["Social welfare functions as governance mechanisms — direct parallel to futarchy/prediction market design"] +processed_by: theseus +processed_date: 2026-03-11 +claims_extracted: ["rlhf-is-implicit-social-choice-without-normative-scrutiny.md", "post-arrow-social-choice-mechanisms-work-by-weakening-independence-of-irrelevant-alternatives.md", "pluralistic-ai-alignment-through-multiple-systems-preserves-value-diversity-better-than-forced-consensus.md", "rlchf-aggregated-rankings-variant-combines-evaluator-rankings-via-social-welfare-function-before-reward-model-training.md", "rlchf-features-based-variant-models-individual-preferences-with-evaluator-characteristics-enabling-aggregation-across-diverse-groups.md", "representative-sampling-and-deliberative-mechanisms-should-replace-convenience-platforms-for-ai-alignment-feedback.md"] +enrichments_applied: ["pluralistic-alignment-must-accommodate-irreducibly-diverse-values-simultaneously-rather-than-converging-on-a-single-aligned-state.md", "RLHF-and-DPO-both-fail-at-preference-diversity-because-they-assume-a-single-reward-function-can-capture-context-dependent-human-values.md", "collective-intelligence-requires-diversity-as-a-structural-precondition-not-a-moral-preference.md", "AI-alignment-is-a-coordination-problem-not-a-technical-problem.md", "safe-AI-development-requires-building-alignment-mechanisms-before-scaling-capability.md"] +extraction_model: "anthropic/claude-sonnet-4.5" +extraction_notes: "Definitive position paper connecting social choice theory to AI alignment. Six new claims extracted covering RLHF as implicit social choice, post-Arrow mechanisms, pluralism option, and RLCHF variants. Five enrichments to existing claims on preference diversity, collective intelligence, and coordination. No entity data. Key insight: mainstream AI alignment is converging toward collective superintelligence thesis through the 'pluralism option' without using that terminology. Stuart Russell co-authorship signals this is now a serious position within AI safety establishment." --- ## Content diff --git a/inbox/archive/2024-08-28-futardio-proposal-proposal-7.md b/inbox/archive/2024-08-28-futardio-proposal-proposal-7.md index 32d6fa4eb..0f82ab720 100644 --- a/inbox/archive/2024-08-28-futardio-proposal-proposal-7.md +++ b/inbox/archive/2024-08-28-futardio-proposal-proposal-7.md @@ -6,13 +6,17 @@ url: "https://www.futard.io/proposal/AuNNyR4oU2zkG1sYBzJ3DJmyDzMKSmSW2yASorWenuC date: 2024-08-28 domain: internet-finance format: data -status: unprocessed +status: null-result tags: [futardio, metadao, futarchy, solana, governance] event_type: proposal processed_by: rio processed_date: 2024-08-28 extraction_model: "anthropic/claude-sonnet-4.5" extraction_notes: "This source contains only metadata about a failed MetaDAO proposal with no proposal text, rationale, market data, or voting details. The source provides verifiable facts (proposal number, accounts, dates, status) but no evidence supporting arguable claims about futarchy mechanisms, governance outcomes, or market behavior. Without proposal content or outcome analysis, there is nothing to extract as claims or enrichments. The existing claim 'MetaDAOs futarchy implementation shows limited trading volume in uncontested decisions' could potentially be enriched if this proposal had volume data, but none is provided. This is purely archival metadata." +processed_by: rio +processed_date: 2026-03-11 +extraction_model: "anthropic/claude-sonnet-4.5" +extraction_notes: "Source contains only metadata about a failed MetaDAO proposal with no proposal text, rationale, market data, or voting details. Created decision_market entity for archival completeness and timeline tracking. No extractable claims or enrichments due to absence of substantive content about mechanisms, outcomes, or governance dynamics. This is purely structural metadata documenting that a proposal existed and failed." --- ## Proposal Details @@ -39,3 +43,11 @@ extraction_notes: "This source contains only metadata about a failed MetaDAO pro - DAO account: GWywkp2mY2vzAaLydR2MBXRCqk2vBTyvtVRioujxi5Ce - Proposer: HwBL75xHHKcXSMNcctq3UqWaEJPDWVQz6NazZJNjWaQc - Autocrat version: 0.3 + + +## Key Facts +- MetaDAO Proposal #7 created 2024-08-28, failed 2024-09-01 +- Proposal account: AuNNyR4oU2zkG1sYBzJ3DJmyDzMKSmSW2yASorWenuC6 +- DAO account: GWywkp2mY2vzAaLydR2MBXRCqk2vBTyvtVRioujxi5Ce +- Proposer: HwBL75xHHKcXSMNcctq3UqWaEJPDWVQz6NazZJNjWaQc +- Autocrat version: 0.3 diff --git a/inbox/archive/2024-11-13-futardio-proposal-cut-emissions-by-50.md b/inbox/archive/2024-11-13-futardio-proposal-cut-emissions-by-50.md index ba308ffaa..a4acd22f6 100644 --- a/inbox/archive/2024-11-13-futardio-proposal-cut-emissions-by-50.md +++ b/inbox/archive/2024-11-13-futardio-proposal-cut-emissions-by-50.md @@ -6,9 +6,13 @@ url: "https://www.futard.io/proposal/6LcxhHS3JvDtbS1GoQS18EgH5Pzf7AnqQpR7D4HxmWp date: 2024-11-13 domain: internet-finance format: data -status: unprocessed +status: null-result tags: [futardio, metadao, futarchy, solana, governance] event_type: proposal +processed_by: rio +processed_date: 2026-03-11 +extraction_model: "anthropic/claude-sonnet-4.5" +extraction_notes: "Source is a futarchy governance proposal for Coal token emission schedule. Extracted as decision_market entity (the proposal itself) and created parent entity for Coal project. No novel claims about futarchy mechanisms - this is a straightforward application of existing governance patterns. The shift from algorithmic to market-driven emission control is notable but represents implementation of known futarchy principles rather than new mechanism insight." --- ## Proposal Details @@ -66,3 +70,10 @@ A follow-up decision market will be held in early January, approximately two mon - Autocrat version: 0.3 - Completed: 2024-11-17 - Ended: 2024-11-17 + + +## Key Facts +- Coal token emission rate reduced from 15.625 to 7.8125 per minute (2024-11-17) +- Coal annual inflation reduced from ~110% to ~56% (2024-11-17) +- Coal completed 6 halvings before governance transition +- Coal proposal 6LcxhHS3JvDtbS1GoQS18EgH5Pzf7AnqQpR7D4HxmWpy passed (2024-11-17)