41554 blogs · [ { "id": "01a0d93a-c8e1-738c-9fa7-b130c36325c9", "title": "How a Group Becomes a Team", "url": "https://june.kim/how-a-group-becomes-a-team/", "published_at": "2026-09-24T00:00:00+00:00" }, { "id": "01a0d93a-c8e1-738c-9fa7-b130c407bccc", "title": "Auditing JevBench", "url": "https://june.kim/auditing-jevbench/", "published_at": "2026-09-21T00:00:00+00:00" }, { "id": "01a0bb45-b6ce-72ff-aa5f-8b79372c0937", "title": "Benchmark-Driven Development", "url": "https://june.kim/benchmark-driven-development/", "published_at": "2026-09-17T00:00:00+00:00" }, { "id": "01a08792-6593-7122-b9fe-2ed388812b7a", "title": "test post", "url": "https://june.kim/test/", "published_at": "2026-08-26T23:06:08+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6253ab817ca", "title": "Facsimile Response", "url": "https://june.kim/facsimile-response/", "published_at": "2026-08-26T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6253ace837d", "title": "Agentic Production System", "url": "https://june.kim/agentic-production-system/", "published_at": "2026-08-17T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6253b15fc2e", "title": "Interface-Driven Code Scavenging", "url": "https://june.kim/interface-driven-code-scavenging/", "published_at": "2026-08-12T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6253b8b0f9e", "title": "Nested Agentic Iteration", "url": "https://june.kim/nested-agentic-iteration/", "published_at": "2026-08-12T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6253c39d74c", "title": "The Bible Is Terminal", "url": "https://june.kim/the-bible-is-terminal/", "published_at": "2026-08-12T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6253c94dd2e", "title": "Replayable Claims: Epistemic Status Without Trusting the Sender", "url": "https://june.kim/local-replay-auditability/", "published_at": "2026-08-11T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6253d17f0d9", "title": "AI Safety is Reinventing the Law", "url": "https://june.kim/ai-safety-is-reinventing-the-law/", "published_at": "2026-08-09T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6253e098f6d", "title": "Auditing SlopCodeBench", "url": "https://june.kim/auditing-slopcodebench/", "published_at": "2026-08-09T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6253e137ec8", "title": "τ²-bench Doesn't Check the Rules", "url": "https://june.kim/tau2-bench-doesnt-check-the-rules/", "published_at": "2026-08-06T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6253e3f5a07", "title": "The Complementarity Test", "url": "https://june.kim/the-complementarity-test/", "published_at": "2026-08-05T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6253f1352f9", "title": "The Virtues of Typed Reasoning", "url": "https://june.kim/the-virtues-of-typed-reasoning/", "published_at": "2026-07-31T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6253ff7f3fa", "title": "Borrowed Vocabulary for the Hypothesis Edge", "url": "https://june.kim/borrowed-vocabulary-for-the-hypothesis-edge/", "published_at": "2026-07-30T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b62540860b36", "title": "Why There Are No Ads in Your Chatbot", "url": "https://june.kim/why-there-are-no-ads-in-your-chatbot/", "published_at": "2026-07-30T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6254176c786", "title": "Intent Extraction in the Wild", "url": "https://june.kim/intent-extraction-in-the-wild/", "published_at": "2026-07-28T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6254271a860", "title": "The agent is the inbox", "url": "https://june.kim/the-agent-is-the-inbox/", "published_at": "2026-07-26T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b625431ccb90", "title": "Auditing Frontier-Bench", "url": "https://june.kim/auditing-frontier-bench/", "published_at": "2026-07-24T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b62543db9878", "title": "Assurance at the Boundary: The Level Below AAL-1", "url": "https://june.kim/assurance-at-the-boundary/", "published_at": "2026-07-19T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b62544063230", "title": "Game of Benches", "url": "https://june.kim/game-of-benches/", "published_at": "2026-07-19T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b625447063f3", "title": "An Epistemic Ablation", "url": "https://june.kim/an-epistemic-ablation/", "published_at": "2026-07-18T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b62544e43534", "title": "Auditing FrontierCode", "url": "https://june.kim/auditing-frontiercode/", "published_at": "2026-07-18T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b625457fa2c6", "title": "Auditing MirrorCode", "url": "https://june.kim/auditing-mirrorcode/", "published_at": "2026-07-17T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b62545861f3a", "title": "Vulnerability Disclosure Queue Overload", "url": "https://june.kim/vulnerability-disclosure-needs-congestion-control/", "published_at": "2026-07-16T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b62545bf761d", "title": "Compensating Controls", "url": "https://june.kim/compensating-controls/", "published_at": "2026-07-13T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6254612301b", "title": "PPC Science", "url": "https://june.kim/ppc-science/", "published_at": "2026-07-13T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b625466de82d", "title": "Adtech Is an Accounting Problem", "url": "https://june.kim/adtech-is-an-accounting-problem/", "published_at": "2026-07-12T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b62546a127fc", "title": "Hiring Is Evals", "url": "https://june.kim/hiring-is-evals/", "published_at": "2026-07-11T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b625476f3a86", "title": "797,444 Impressions, 7 Clicks", "url": "https://june.kim/impressions-and-clicks/", "published_at": "2026-07-11T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b62547dd44d4", "title": "How to Audit a Benchmark", "url": "https://june.kim/how-to-audit-a-benchmark/", "published_at": "2026-07-10T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b62548ac3e48", "title": "Trust Is a Cache", "url": "https://june.kim/trust-is-a-cache/", "published_at": "2026-07-10T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b625499e62df", "title": "Terminal-Bench Is Blind to Destruction", "url": "https://june.kim/terminal-bench-frame/", "published_at": "2026-07-09T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b62549f2b7ed", "title": "Auditing DeepSWE v1.1", "url": "https://june.kim/auditing-deepswe-v1-1/", "published_at": "2026-07-07T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6254a2fb452", "title": "Nodewise E-Values Under Graph Interference: Causal Abuse Filtering for Agent Platforms", "url": "https://june.kim/nodewise-e-values/", "published_at": "2026-07-06T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6254ab6bba3", "title": "The Power Diagram Auction: A Formally Verified VCG Mechanism for LLM Advertising", "url": "https://june.kim/power-diagram-auction/", "published_at": "2026-07-06T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6254ac68d92", "title": "Regeneration Re-Prices Contamination", "url": "https://june.kim/reprice-contamination/", "published_at": "2026-07-06T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6254b28cafd", "title": "Who Authored the Spec? Evidence for the Line-Drawing Question Thaler Left Open", "url": "https://june.kim/who-authored-the-spec/", "published_at": "2026-07-06T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6254b466497", "title": "Union-Find Compaction: Provenance-Preserving Context Compression for LLM Agents", "url": "https://june.kim/provenance-preserving-compaction/", "published_at": "2026-07-05T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6254ba108ad", "title": "The Kilogram Was Losing Weight", "url": "https://june.kim/the-kilogram-was-losing-weight/", "published_at": "2026-07-04T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6254c31e169", "title": "ProgramBench Measures Recall", "url": "https://june.kim/programbench-measures-recall/", "published_at": "2026-06-27T00:00:00+00:00" }, { "id": "01a08792-6591-73f9-b67a-b6254c769d27", "title": "Generalize or Specialize? Retaining Reusable Skills for World-Model Agents", "url": "https://june.kim/generalize-or-specialize/", "published_at": "2026-06-26T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f56e118112", "title": "Detecting and Refining Ambiguous Specifications, Automatically (DRAFT)", "url": "https://june.kim/detect-refine-ambiguous-specifications/", "published_at": "2026-06-22T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f56ed3bfa5", "title": "A Determinacy Audit of SWE-bench Pro", "url": "https://june.kim/a-determinacy-audit-of-swebench-pro/", "published_at": "2026-06-21T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f56f29500f", "title": "Go Check", "url": "https://june.kim/go-check/", "published_at": "2026-06-15T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f570155cf2", "title": "Verifiable Knowledge", "url": "https://june.kim/verifiable-knowledge/", "published_at": "2026-06-13T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f570de2dd1", "title": "You Cannot Ring a Semiring", "url": "https://june.kim/tempus-doxa-praxis/", "published_at": "2026-06-12T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f571c05e21", "title": "What Cannot Be False Cannot Be True", "url": "https://june.kim/what-cannot-be-false-cannot-be-true/", "published_at": "2026-06-12T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f572591fe2", "title": "Wrong Again", "url": "https://june.kim/wrong-again/", "published_at": "2026-06-11T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f572b9d534", "title": "Wrong Questions", "url": "https://june.kim/wrong-questions/", "published_at": "2026-06-11T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f573393efc", "title": "Compress and Unfold", "url": "https://june.kim/compress-and-unfold/", "published_at": "2026-06-10T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f57378da29", "title": "How Not to Run SWE-bench Pro", "url": "https://june.kim/how-not-to-run-swebench-pro/", "published_at": "2026-06-08T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f573d711cd", "title": "Precisely Wrong", "url": "https://june.kim/type-iii-error/", "published_at": "2026-06-07T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f574c89902", "title": "Truly Untrue?", "url": "https://june.kim/truly-untrue/", "published_at": "2026-06-06T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f57557ca48", "title": "Truth Is Buildable", "url": "https://june.kim/truth-is-buildable/", "published_at": "2026-06-04T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f575a355f3", "title": "Sour Red Tapes", "url": "https://june.kim/sour-red-tapes/", "published_at": "2026-06-01T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f576101094", "title": "The Hypothesis Graph: A Verifiable Semantic Memory for Coding Agents", "url": "https://june.kim/the-hypothesis-graph-semantic-memory-methodeutics/", "published_at": "2026-05-28T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f576d7ffe5", "title": "Auditing DeepSWE", "url": "https://june.kim/auditing-deepswe/", "published_at": "2026-05-27T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f57771f6d9", "title": "Red-Teaming Human-Likeness", "url": "https://june.kim/red-teaming-human-likeness/", "published_at": "2026-05-24T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f577be4d21", "title": "85% on SWE-bench Verified, 97% of eligible", "url": "https://june.kim/swebench-verified/", "published_at": "2026-05-24T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f577d9a5b1", "title": "Make No Mistakes", "url": "https://june.kim/make-no-mistakes/", "published_at": "2026-05-17T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f578b1c35b", "title": "Papiermark Credentials", "url": "https://june.kim/papiermark-credentials/", "published_at": "2026-05-17T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f579b07168", "title": "Chewy TUI", "url": "https://june.kim/chewy-tui/", "published_at": "2026-05-15T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f579b26730", "title": "Internal Reasoning of Prose Compiler", "url": "https://june.kim/internal-reasoning-of-prose-compiler/", "published_at": "2026-05-15T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f579e77256", "title": "(Issue) → PR", "url": "https://june.kim/issue-to-pr/", "published_at": "2026-05-14T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f57ab14cb1", "title": "(PR) → merged", "url": "https://june.kim/pr-to-merged/", "published_at": "2026-05-14T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f57b946245", "title": "Speedrunning Open Source", "url": "https://june.kim/speedrunning-open-source/", "published_at": "2026-05-12T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f57c7112cb", "title": "Abduction Tuner", "url": "https://june.kim/abduction-tuner-null-result/", "published_at": "2026-05-10T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f57c935792", "title": "Provenance Has No Half-Life", "url": "https://june.kim/provenance-has-no-half-life/", "published_at": "2026-05-10T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f57d11dc0d", "title": "The Rest of the Owl", "url": "https://june.kim/rest-of-the-owl/", "published_at": "2026-05-10T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f57db147fd", "title": "Complementations", "url": "https://june.kim/complementations/", "published_at": "2026-05-09T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f57e62ab68", "title": "Arbor", "url": "https://june.kim/arbor/", "published_at": "2026-05-08T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f57eb4f298", "title": "Sweep & Triage", "url": "https://june.kim/sweep-and-triage/", "published_at": "2026-05-08T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f57f80d26e", "title": "Investigate", "url": "https://june.kim/investigate/", "published_at": "2026-05-07T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f57fe2929c", "title": "Abduction", "url": "https://june.kim/abduction/", "published_at": "2026-05-04T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f580b71650", "title": "Allergic to Slop", "url": "https://june.kim/allergic-to-slop/", "published_at": "2026-05-04T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f5819d0895", "title": "Modes of Reason", "url": "https://june.kim/modes-of-reason/", "published_at": "2026-05-04T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f581b513c5", "title": "StarCraft 2 Is the Ideal Benchmark", "url": "https://june.kim/sc2-benchmark/", "published_at": "2026-05-04T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f582950a9f", "title": "Never Intercept Payments", "url": "https://june.kim/never-intercept-payments/", "published_at": "2026-05-01T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f582e955b5", "title": "Parenting Horizons", "url": "https://june.kim/parenting-horizons/", "published_at": "2026-05-01T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f583112615", "title": "Before You Compose", "url": "https://june.kim/before-you-compose/", "published_at": "2026-04-29T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f583a8b1ca", "title": "The Hypothesis Graph", "url": "https://june.kim/the-hypothesis-graph/", "published_at": "2026-04-28T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f583cb25a9", "title": "Evidence has a trajectory", "url": "https://june.kim/evidence-has-a-trajectory/", "published_at": "2026-04-27T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f5846e2eb5", "title": "Belief is the edge of knowing", "url": "https://june.kim/belief-is-the-edge-of-knowing/", "published_at": "2026-04-26T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f5852e72ae", "title": "Prayer is alignment", "url": "https://june.kim/prayer-is-alignment/", "published_at": "2026-04-26T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f585368743", "title": "Contract by label", "url": "https://june.kim/contract-by-label/", "published_at": "2026-04-25T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f5855a8240", "title": "Four schools of programming", "url": "https://june.kim/four-schools-of-programming/", "published_at": "2026-04-25T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f585614a6e", "title": "Agentic Dev Setup 2026", "url": "https://june.kim/agentic-dev-setup/", "published_at": "2026-04-24T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f586431408", "title": "Soar Already Does Async", "url": "https://june.kim/soar-already-async/", "published_at": "2026-04-23T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f5864ea8c6", "title": "Junebot", "url": "https://june.kim/dual-audience/", "published_at": "2026-04-19T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f5868c2663", "title": "Science on Trial", "url": "https://june.kim/science-on-trial/", "published_at": "2026-04-19T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f586ac0cbf", "title": "Does LLM Iteration Mitigate Against Slop-Slope?", "url": "https://june.kim/does-iteration-mitigate-slop-slope/", "published_at": "2026-04-18T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f587870100", "title": "Union Found", "url": "https://june.kim/union-found/", "published_at": "2026-04-17T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f588330830", "title": "Close the Loop", "url": "https://june.kim/close-the-loop-design/", "published_at": "2026-04-14T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f5889a3309", "title": "Computational Theology", "url": "https://june.kim/computational-theology/", "published_at": "2026-04-14T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f5889c6a03", "title": "History Is a DAG", "url": "https://june.kim/history-is-a-dag/", "published_at": "2026-04-14T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f589447a39", "title": "Prework", "url": "https://june.kim/prework/", "published_at": "2026-04-14T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f589f6b939", "title": "The Prereg Checklist", "url": "https://june.kim/the-prereg-checklist/", "published_at": "2026-04-14T00:00:00+00:00" }, { "id": "01a08792-6592-735f-876a-11f589fdd467", "title": "Bug Hunt", "url": "https://june.kim/bug-hunt/", "published_at": "2026-04-13T00:00:00+00:00" } ] posts Claim your blog

Back to kimjune01

Blog · corpus.blog/blogs/june.kim/posts

kimjune01

june.kim

2026

How a Group Becomes a Team original ↗

24 Sept 2026

Auditing JevBench original ↗

21 Sept 2026

Benchmark-Driven Development original ↗

17 Sept 2026

test post original ↗

26 Aug 2026

Facsimile Response original ↗

26 Aug 2026

Agentic Production System original ↗

17 Aug 2026

Interface-Driven Code Scavenging original ↗

12 Aug 2026

Nested Agentic Iteration original ↗

12 Aug 2026

The Bible Is Terminal original ↗

12 Aug 2026

Replayable Claims: Epistemic Status Without Trusting the Sender original ↗

11 Aug 2026

AI Safety is Reinventing the Law original ↗

9 Aug 2026

Auditing SlopCodeBench original ↗

9 Aug 2026

τ²-bench Doesn't Check the Rules original ↗

6 Aug 2026

The Complementarity Test original ↗

5 Aug 2026

The Virtues of Typed Reasoning original ↗

31 Jul 2026

Borrowed Vocabulary for the Hypothesis Edge original ↗

30 Jul 2026

Why There Are No Ads in Your Chatbot original ↗

30 Jul 2026

Intent Extraction in the Wild original ↗

28 Jul 2026

The agent is the inbox original ↗

26 Jul 2026

Auditing Frontier-Bench original ↗

24 Jul 2026

Assurance at the Boundary: The Level Below AAL-1 original ↗

19 Jul 2026

Game of Benches original ↗

19 Jul 2026

An Epistemic Ablation original ↗

18 Jul 2026

Auditing FrontierCode original ↗

18 Jul 2026

Auditing MirrorCode original ↗

17 Jul 2026

Vulnerability Disclosure Queue Overload original ↗

16 Jul 2026

Compensating Controls original ↗

13 Jul 2026

PPC Science original ↗

13 Jul 2026

Adtech Is an Accounting Problem original ↗

12 Jul 2026

Hiring Is Evals original ↗

11 Jul 2026

797,444 Impressions, 7 Clicks original ↗

11 Jul 2026

How to Audit a Benchmark original ↗

10 Jul 2026

Trust Is a Cache original ↗

10 Jul 2026

Terminal-Bench Is Blind to Destruction original ↗

9 Jul 2026

Auditing DeepSWE v1.1 original ↗

7 Jul 2026

Nodewise E-Values Under Graph Interference: Causal Abuse Filtering for Agent Platforms original ↗

6 Jul 2026

The Power Diagram Auction: A Formally Verified VCG Mechanism for LLM Advertising original ↗

6 Jul 2026

Regeneration Re-Prices Contamination original ↗

6 Jul 2026

Who Authored the Spec? Evidence for the Line-Drawing Question Thaler Left Open original ↗

6 Jul 2026

Union-Find Compaction: Provenance-Preserving Context Compression for LLM Agents original ↗

5 Jul 2026

The Kilogram Was Losing Weight original ↗

4 Jul 2026

ProgramBench Measures Recall original ↗

27 Jun 2026

Generalize or Specialize? Retaining Reusable Skills for World-Model Agents original ↗

26 Jun 2026

Detecting and Refining Ambiguous Specifications, Automatically (DRAFT)original ↗

22 Jun 2026

A Determinacy Audit of SWE-bench Pro original ↗

21 Jun 2026

Go Check original ↗

15 Jun 2026

Verifiable Knowledge original ↗

13 Jun 2026

You Cannot Ring a Semiring original ↗

12 Jun 2026

What Cannot Be False Cannot Be True original ↗

12 Jun 2026

Wrong Again original ↗

11 Jun 2026

Wrong Questions original ↗

11 Jun 2026

Compress and Unfold original ↗

10 Jun 2026

How Not to Run SWE-bench Pro original ↗

8 Jun 2026

Precisely Wrong original ↗

7 Jun 2026

Truly Untrue?original ↗

6 Jun 2026

Truth Is Buildable original ↗

4 Jun 2026

Sour Red Tapes original ↗

1 Jun 2026

The Hypothesis Graph: A Verifiable Semantic Memory for Coding Agents original ↗

28 May 2026

Auditing DeepSWE original ↗

27 May 2026

Red-Teaming Human-Likeness original ↗

24 May 2026

85% on SWE-bench Verified, 97% of eligible original ↗

24 May 2026

Make No Mistakes original ↗

17 May 2026

Papiermark Credentials original ↗

17 May 2026

Chewy TUI original ↗

15 May 2026

Internal Reasoning of Prose Compiler original ↗

15 May 2026

(Issue) → PR original ↗

14 May 2026

(PR) → merged original ↗

14 May 2026

Speedrunning Open Source original ↗

12 May 2026

Abduction Tuner original ↗

10 May 2026

Provenance Has No Half-Life original ↗

10 May 2026

The Rest of the Owl original ↗

10 May 2026

Complementations original ↗

9 May 2026

Arbor original ↗

8 May 2026

Sweep & Triage original ↗

8 May 2026

Investigate original ↗

7 May 2026

Abduction original ↗

4 May 2026

Allergic to Slop original ↗

4 May 2026

Modes of Reason original ↗

4 May 2026

StarCraft 2 Is the Ideal Benchmark original ↗

4 May 2026

Never Intercept Payments original ↗

1 May 2026

Parenting Horizons original ↗

1 May 2026

Before You Compose original ↗

29 Apr 2026

The Hypothesis Graph original ↗

28 Apr 2026

Evidence has a trajectory original ↗

27 Apr 2026

Belief is the edge of knowing original ↗

26 Apr 2026

Prayer is alignment original ↗

26 Apr 2026

Contract by label original ↗

25 Apr 2026

Four schools of programming original ↗

25 Apr 2026

Agentic Dev Setup 2026 original ↗

24 Apr 2026

Soar Already Does Async original ↗

23 Apr 2026

Junebot original ↗

19 Apr 2026

Science on Trial original ↗

19 Apr 2026

Does LLM Iteration Mitigate Against Slop-Slope?original ↗

18 Apr 2026

Union Found original ↗

17 Apr 2026

Close the Loop original ↗

14 Apr 2026

Computational Theology original ↗

14 Apr 2026

History Is a DAG original ↗

14 Apr 2026

Prework original ↗

14 Apr 2026

The Prereg Checklist original ↗

14 Apr 2026

Bug Hunt original ↗

13 Apr 2026