{"id":"91a5f2a3-a0b4-459a-b0c2-3818e4ede97a","timestamp":1775104650165,"matcher":{"static":{"/__nuxt_content/index/sql_dump.txt":{"prerender":true},"/__nuxt_content/projects/sql_dump.txt":{"prerender":true},"/__nuxt_content/blog/sql_dump.txt":{"prerender":true},"/__nuxt_content/pages/sql_dump.txt":{"prerender":true},"/__nuxt_content/about/sql_dump.txt":{"prerender":true}},"wildcard":{},"dynamic":{}},"prerendered":["/","/projects","/about","/blog/agentic-ai-is-becoming-a-cybersecurity-problem","/blog/openclaw-a-viral-agent-and-the-supply-chain-reality-check","/blog/prism-and-the-architecture-of-artifact-native-ai-for-science","/blog/order-books-are-the-battlefield","/blog","/blog/gpai-obligations-begin-what-changes-for-model-providers-and-enterprises","/blog/reference-architecture-v2-the-operable-agent-platform","/blog/the-connector-ecosystem-mcp-adoption-patterns-versioning-and-governance","/blog/voice-agents-you-can-operate-reliability-caching-latency-human-handoff","/blog/the-1m-token-era-long-context-retrieval-economics-and-system-design","/blog/multi-agent-systems-without-chaos-supervisors-specialists-and-coordination-contracts","/blog/security-for-agent-connectors-least-privilege-injection-resistance-and-safe-toolchains","/blog/agents-as-distributed-systems-outbox-sagas-eventually-correct-workflows","/blog/the-compliance-cliff-prohibited-practices-and-governance-controls-that-actually-ship","/blog/agent-runtimes-emerge-sdks-orchestration-primitives-and-observability","/blog/agent-evals-as-ci-from-prompt-tests-to-scenario-harnesses-and-red-teams","/blog/standards-for-the-agent-ecosystem-connectors-protocols-and-mcp","/blog/computer-use-agents-in-production-sandboxes-vms-ui-action-safety","/blog/regulation-as-architecture-eu-ai-act-controls-evidence","/blog/rag-you-can-evaluate-retrieval-pipelines-reranking-citations-truth-boundaries","/blog/reasoning-budgets-fast-slow-paths-verification-think-longer","/blog/real-time-agents-streaming-barge-in-session-state-that-doesnt-collapse","/blog/open-weights-in-production-evaluation-licensing-and-guardrails","/blog/multimodal-changes-ux-designing-text-vision-audio-systems","/blog/tool-use-with-open-models-function-calling-sandboxes-capability-boundaries","/blog/model-selection-becomes-architecture-routing-budgets-and-capability-tiers","/blog/tool-use-and-agents-when-the-model-becomes-a-workflow-engine","/blog/long-context-isnt-memory-when-to-stuff-when-to-retrieve","/blog/context-assembly-as-a-subsystem-summaries-state-and-token-budgets","/blog/midjourney-and-the-product-loop-why-some-generators-feel-magical","/blog/dalle-how-text-became-images-and-why-it-changed-everything","/blog/rag-done-right-knowledge-grounding-and-evaluation-that-isnt-vibes","/blog/hallucinations-a-probabilistic-failure-mode-not-a-moral-defect","/blog/prompting-is-not-programming-contracts-schemas-failure-budgets","/blog/rlhf-stabilizing-behavior-with-preferences-alignment-as-control","/blog/dissecting-chatgpt-the-product-architecture-around-the-model","/blog/transformers-attention-as-an-engineering-breakthrough","/blog/instruction-tuning-turning-a-completion-engine-into-an-assistant","/blog/why-nlp-was-hard-rnn-pain-vanishing-gradients-limits-of-memory","/blog/pretraining-is-compression-tokens-datasets-and-emergent-skill","/blog/capstone-build-a-system-that-can-survive","/blog/software-in-the-age-of-probabilistic-components","/blog/cost-as-a-first-class-constraint-finops-for-architects","/blog/data-engineering-for-product-teams-oltp-vs-olap-streaming-and-truth","/blog/cloud-infrastructure-without-the-religion","/blog/incident-response-and-resilience-designing-for-failure-not-hope","/blog/performance-engineering-end-to-end-from-ttfb-to-tail-latency","/blog/api-evolution-at-scale-compatibility-contracts-consumer-driven-testing","/blog/distributed-data-transactions-outbox-sagas-eventually-correct","/blog/security-for-builders-threat-modeling-and-secure-by-default-systems","/blog/observability-that-works-logs-metrics-traces-and-slo-thinking","/blog/ci-cd-as-architecture-testing-pyramids-pipelines-rollout-safety","/blog/containers-docker-and-the-discipline-of-reproducibility","/blog/data-stores-101-for-architects-sql-nosql-consistency","/blog/caching-without-folklore-redis-cdns-and-the-two-hard-things","/blog/microservices-vs-modular-monolith-when-and-how","/blog/queues-retries-and-idempotency-engineering-reality-in-async-systems","/blog/restful-design-that-survives-resources-boundaries-and-versioning","/blog/frontend-systems-routing-state-forms-boring-stack","/blog/backends-frameworks-dont-matter-until-they-do","/blog/from-research-rig-to-system-2020-postmortem","/blog/bitmex-management-gym-position-sizing-first-risk-aware-agent","/blog/browser-reality-event-loop-rendering-ux-bugs-backend-bugs","/blog/http-as-a-distributed-systems-api-without-the-buzzwords","/blog/batch-training-evaluation-again-promising-results-that-survive-scrutiny","/blog/deep-silos-in-rl-architecture-as-stability","/blog/react-as-an-architecture-tool-components-hooks-cost-of-rerendering","/blog/ajax-fetch-graphql-trpc-choosing-your-data-boundary","/blog/webs-compression-algorithm-static-web2-spa-ssr-edge","/blog/constraints-that-teach-risk-caps-timeouts-surviving-bad-regimes","/blog/first-live-runs-small-size-big-lessons","/blog/maker-trades-fees-reward-signal","/blog/chappie-wiring-from-trained-policy-to-running-process","/blog/safety-engineering-kill-switches-reconciliation-failure-recovery","/blog/reward-shaping-without-lying","/blog/live-alpha-monitoring-when-market-talks-back","/blog/bitmex-gym-baseline-trading-environment-where-cheating-starts","/blog/the-503-lesson-outages-as-signal-not-just-a-bug","/blog/supervised-baselines-first-alpha-models","/blog/evaluation-discipline-walk-forward-backtesting-inside-gym","/blog/from-prediction-to-decision-trading-environment-contract","/blog/deep-silos-representation-learning-feature-families","/blog/the-collector-websockets-clock-drift-and-the-first-clean-snapshot","/blog/dataset-reality-hdf5-schema-missing-data","/blog/defining-alpha-without-cheating","/blog/from-microstructure-to-features-what-the-model-will-see","/blog/imitation-learning-gail-and-learning-from-experts","/blog/stability-is-a-feature-you-have-to-design","/blog/normalization-is-a-deployment-problem","/blog/sparse-rewards-her-and-learning-from-what-didnt-happen","/blog/actor-critic-the-first-time-rl-feels-trainable","/blog/feature-engineering-microstructure-liquidity-created-removed","/blog/rewards-returns-learning-is-an-interface-problem","/blog/why-rl-training-is-unstable-a-catalog-of-breakage","/blog/continuous-control-ddpg-and-the-seduction-of-off-policy","/blog/the-pain-of-training-rnns","/blog/lstms-engineering-memory-into-the-network","/blog/bandits-the-first-honest-rl-problem","/blog/function-approximation-the-day-rl-stopped-being-stable","/blog/deep-q-learning-my-first-real-baselines-month","/blog/policy-gradients-learning-without-a-value-crutch","/blog/tabular-rl-when-value-iteration-feels-like-cheating","/blog/pooling-hierarchies-and-cnns","/blog/from-ml-to-deep-learning-retrospective","/blog/enter-recurrent-neural-networks","/blog/optimization-got-real-momentumand-learning-rates","/blog/convolutions-why-cnns-see-the-world-differently","/blog/why-deeper-networks-are-harder-to-train","/blog/anomaly-detection-and-recommenders","/blog/from-logistic-regression-to-neurons","/blog/activation-functions-are-not-a-detail","/blog/initialization-scale-fragility-of-deep-networks","/blog/backpropagation-demystified","/blog/neural-networks-learning-backpropagation","/blog/support-vector-machines","/blog/unsupervised-learning-and-compression","/blog/intro-to-neural-networks","/blog/debugging-ml-bias-variance","/blog/linear-regression-with-multiple-vars","/blog/normal-equation-vs-gradient-descent","/blog/regularization-overfitting-in-the-real-world","/blog/logistic-regression-for-classification","/blog/linear-regression-from-scratch","/blog/why-im-learning-machine-learning"]}