-
5426026908
docs: regenerate weekly report (2026-05-18)
main
Rodin
2026-05-18 16:10:16 +00:00
-
afbc013e2e
finding #80: config-a/b dispatcher malfunction detected in multi-model review pipeline (3.5x cost overage)
Rodin
2026-05-15 08:37:01 +00:00
-
8e64f8f012
finding(79): multi-model security review catches HTTPS bypass in GitHub client (PR #131)
Rodin
2026-05-14 21:56:58 +00:00
-
643a804bdf
finding #79: multi-model security review catches CGN + proxy-assisted SSRF gaps
Rodin
2026-05-14 12:24:54 +00:00
-
f9523d46b1
data: dev loop effectiveness analysis (2026-05-14)
aweiker
2026-05-14 06:54:42 +00:00
-
828da269c0
docs: regenerate weekly report (2026-05-11)
Rodin
2026-05-11 09:04:35 -07:00
-
2ca8c974f3
Add finding #25: Data integrity analysis on audit-log.md
Rodin
2026-05-11 08:49:32 -07:00
-
ac55ecdb98
Finding 28: Regulatory compliance analysis on wash sale tracking
Rodin
2026-05-11 00:29:12 -07:00
-
2b10595bff
Finding #68: Cross-context contract coherence analysis
Rodin
2026-05-10 21:47:27 -07:00
-
0f43934cb8
Add finding #67: Inter-document contradiction analysis
Rodin
2026-05-10 18:32:45 -07:00
-
bb50188e63
Add Finding #30: Boundary violation analysis on context README
Rodin
2026-05-10 17:28:54 -07:00
-
8adf09b3fb
Add security boundary analysis experiment (2026-05-10)
Rodin
2026-05-10 16:05:45 -07:00
-
c1eb97ed6c
Add finding #65: Temporal correctness analysis (new lens)
Rodin
2026-05-10 14:50:56 -07:00
-
398f33aad4
Finding #64: Regulatory implementation gap analysis
Rodin
2026-05-10 12:30:20 -07:00
-
7c64712c2f
Add finding #65: concurrent write hazards in event sourcing
Rodin
2026-05-10 11:48:41 -07:00
-
873591877d
Finding #64: Specification gap analysis - new analytical lens
Rodin
2026-05-10 11:10:33 -07:00
-
b9036401c2
Finding #63: External System Assumptions Analysis
Rodin
2026-05-10 02:27:53 -07:00
-
ce4801e8a3
Add Finding #62: Boundary contract analysis (new analytical lens)
Rodin
2026-05-09 23:35:36 -07:00
-
9f15047892
Finding #62: Data integrity analysis on signal-lifecycle.md
Rodin
2026-05-09 22:26:46 -07:00
-
527e71a1d6
finding #61: regulatory completeness analysis lens
Rodin
2026-05-09 20:06:51 -07:00
-
af950a33d1
Add finding #60: Counterfactual event ordering analysis
Rodin
2026-05-09 18:28:40 -07:00
-
2988f31fc3
finding 59: convention rule gap analysis
Rodin
2026-05-09 17:28:53 -07:00
-
98304604ac
Finding 58: State machine completeness analysis on kill-switch.md
Rodin
2026-05-09 15:06:32 -07:00
-
faaa6d9c11
Finding #57: Event flow correctness analysis - new analytical lens
Rodin
2026-05-09 13:29:58 -07:00
-
b7acbd7662
Finding #56: Operational burden analysis - new analytical lens
claw
2026-05-09 06:46:29 -07:00
-
5ee0cff3a8
experiment #55: state reconstruction correctness — new analytical lens
claw
2026-05-09 05:06:45 -07:00
-
bb191e48d1
finding #54: wash sale multi-model design review analysis
claw
2026-05-09 03:35:12 -07:00
-
9d0a94bd68
Add finding #53: unstated constraint detection on state machines
Rodin
2026-05-08 23:47:51 -07:00
-
c1ca8cfe46
finding #52: degraded-mode propagation analysis (new lens)
claw
2026-05-08 14:29:29 -07:00
-
79915d1dc3
finding 51: implementation ambiguity analysis — new analytical lens
claw
2026-05-08 12:46:32 -07:00
-
5b8f8caf8c
finding 50: concurrency and race condition analysis lens
claw
2026-05-08 11:06:06 -07:00
-
7ca01f0cbf
finding 49: adversarial evasion/tampering analysis on audit-log.md
claw
2026-05-08 09:09:58 -07:00
-
8f9e87415e
finding #48: defense-in-depth gap analysis on auth-and-credentials.md
claw
2026-05-08 03:47:09 -07:00
-
f3266ccc13
finding 47: emergent behavior from rule composition - new analytical lens
claw
2026-05-08 02:06:25 -07:00
-
b5b5b64a40
finding #46: operational blind spot analysis — new task type
claw
2026-05-08 00:27:23 -07:00
-
64fdfebed3
finding 45: operator decision support gap analysis — new task type
claw
2026-05-07 21:07:46 -07:00
-
e127e7b0c7
finding 44: cross-doc consistency on closely related docs
claw
2026-05-07 19:27:20 -07:00
-
d8a030d9e9
finding #43: opus + narrow framing for contradiction detection
claw
2026-05-07 16:05:14 -07:00
-
296bb21eb7
finding #42: failure propagation chain analysis on system-overview.md
claw
2026-05-07 14:28:26 -07:00
-
a65c471a3f
finding 41: temporal ordering dependency analysis on kill-switch.md
claw
2026-05-07 12:47:03 -07:00
-
bb0c0d564b
Finding #40: Silent data corruption paths in financial accounting
claw
2026-05-07 11:09:58 -07:00
-
0c632c255a
finding #39: narrow framing does not close Sonnet-GPT-5 gap for semantic consistency
claw
2026-05-07 09:26:08 -07:00
-
d27ce6f5e1
finding #38: regulatory compliance gap analysis (FINRA/PDT domain knowledge test)
claw
2026-05-07 07:47:11 -07:00
-
58e69e21f8
finding 37: cross-doc consistency on tightly coupled risk docs
claw
2026-05-07 04:29:23 -07:00
-
c071ffc31f
Finding #36: Compositional interface analysis - two-document interface assumptions
claw
2026-05-07 02:48:46 -07:00
-
d8ddbc9861
mark adversarial ensemble question as answered (finding #35)
claw
2026-05-06 21:29:35 -07:00
-
8338ae3019
finding #35: adversarial ensemble (critique+extend) produces 30% more coverage
claw
2026-05-06 21:29:17 -07:00
-
4a69a99d05
finding #34: information flow hazard analysis on lot-accounting.md
Rodin
2026-05-06 18:29:06 -07:00
-
20c0bd2492
feat: experiment #33 — observability gap analysis on aggregation.md
Rodin
2026-05-06 11:49:05 -07:00
-
8cfabfdc55
experiment #32: testability analysis — new analytical lens
Rodin
2026-05-06 10:09:05 -07:00
-
ee3063997a
finding #31: spec-gap analysis on continuous-risk-monitoring.md
Rodin
2026-05-06 08:27:00 -07:00
-
cfcad67baa
feat: add generic review prompts and generation guide
Rodin
2026-05-06 08:00:59 -07:00
-
a3aebc7cc1
docs(readme): add Reports section with links to REPORT.md and LESSONS.md
Rodin
2026-05-06 07:29:03 -07:00
-
b832f32a16
docs: add generation timestamps to REPORT.md and LESSONS.md
Rodin
2026-05-06 07:26:48 -07:00
-
f865a0d778
docs: add research report and actionable lessons summary
Rodin
2026-05-06 07:24:12 -07:00
-
6af8a6ee10
refactor(findings): split ALL-FINDINGS.md into per-experiment files
Rodin
2026-05-06 07:15:50 -07:00
-
1b108ff66e
Initial publish: 29 findings, 6 prompts, methodology, open questions
Rodin
2026-05-05 19:13:03 -07:00
-
4aea0d004b
Initial commit
rodin
2026-05-06 02:10:14 +00:00