ISSUE 394 — THE DESK THAT SURVIVES + agent independence discipline#45
Open
isaacsight wants to merge 3 commits into
Open
ISSUE 394 — THE DESK THAT SURVIVES + agent independence discipline#45isaacsight wants to merge 3 commits into
isaacsight wants to merge 3 commits into
Conversation
A critical pass exposed that this session had one model author an issue
and then "audit" its own design, language, and imagery and report it all
passed — the audits were never independent. This adds the discipline to
prevent reviewer theater.
INDEPENDENCE.md (new) is the governing doc: the one test ("what does this
agent know, see, or optimize that the author didn't?"), the five
independence sources (different-model, evidence, adversarial, different
criteria, human-gate), the autocorrelation trap (a same-model "team" is
one model agreeing with itself N times, not N reviewers), a
Mechanical-vs-Judgment taxonomy, a mandatory "Independence source:"
header for every agent, and the heterogeneity policy: exploit kbot's
multi-provider BYOK to run judgment and specialist review agents on a
different provider's model than the author (e.g. Japanese review on a
JP-native model), routed via per-agent config rather than hardcoded.
japanese-editor.md is rewritten as the worked example: it declares its
independence source, adds an evidence-grounding protocol step (usage,
corpus, dictionary, and precedent checks instead of parametric opinion),
and changes its verdict to PASS-TO-HUMAN / NEEDS-REVISION — it escalates
to a native reader, it never certifies.
designer.md and reviewer.md get the Independence-source header as the
start of rollout: mechanical findings are trustworthy through tools (cite
the tool or number), but taste and judgment findings are flagged as
non-independent on the author's own model unless run on a different model
or staged for a human. Self-agreement is not assurance.
https://claude.ai/code/session_01X9H4TPZ1aT8Ep4TCkiDzfv
Completes the independence discipline started in the prior commit. Rollout: the "Independence source" header is now on all 53 agents (previously only designer/reviewer/japanese-editor). Each is classified and declares its source honestly: - mechanical — tool is the independence (qa, debugger, deployer, devops, ship, github, environment, hardware, performance, pulse, sync, autopoiesis, stream-auditor); cite the tool, don't assert from memory. - mixed/adversarial — security, hacker, immune: tools + hunt-to-reject, prefer a different model for novel-attack reasoning. - mixed/evidence — documenter, obsidian-sync, rival-intel, admin, replit, speed-of-light: ground claims in artifacts. - judgment — taste/strategy/creative agents (pixel-artist, product, playtester, the strategy set, video/creative set, architects): NOT independent on the author's model; run on a different-provider model via kbot BYOK or stage for a human; never report self-agreement as assurance. - authoring — magazine-editor: independence comes from downstream review plus a human, not self-check. Proof: re-ran ISSUE 391's Japanese through a genuinely different model (GPT-OSS-20B, different provider/weights). It caught five strings the original same-model self-review had passed — demonstrating the autocorrelation the doctrine predicts. It also false-flagged an intentional house phrase, confirming the converse: a decorrelated model surfaces candidates, but a native human is the final authority. 391's Japanese is unchanged; the candidates are staged for human adjudication, exactly as japanese-editor.md now prescribes. https://claude.ai/code/session_01X9H4TPZ1aT8Ep4TCkiDzfv
The craft essay originally drafted as ISSUE 392 in PR #45 collided with the 392 already merged to main (NEVER SELL THE FIXTURES, PR #47). Per the work-review decision, it keeps its place in the catalog at the next open number, 394, rather than being dropped. Content unchanged from the original draft: essay (field-piece, 369 template), kraft stock + classic layout + coffee accent + BY HAND seal; a deliberate restoration of range after the 388–393 agentic run, carrying 391's "the hand survives" thread into the analog objects beside the screen. Renumber-only edits: ISSUE_392→ISSUE_394, number '392'→'394', dateline bumped MAY→JUNE / V·26→VI·26 to sit with the 392/393 June run, back-cover image copied to public/back-covers/394-desk.jpg, attribution and header comments renumbered. Registered ISSUE_394 in index.ts (now LATEST_ISSUE); bumped PUBLISHING.md footer to 394; logged the rebase/renumber in SCRATCHPAD. Stacks on the agent-independence discipline already in this branch. Gate: npm run build (tsc && vite build) green, exit 0. Co-authored-by: Claude <noreply@anthropic.com>
isaacsight
force-pushed
the
claude/ai-news-updates-2u3wb
branch
from
ee28215 to
290d189
Compare
isaacsight
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Rebased onto current
mainand renumbered to resolve an issue-number collision. This branch was opened off#44and still carried two thingsmainnever received.What changed in this rebase
The essay originally drafted here as ISSUE 392 collided with the 392 already merged to main (NEVER SELL THE FIXTURES, PR #47). Per the documented house workflow (PUBLISHING.md §III.1 / §VII — "renumber to the next free slot rather than fighting over the number; both issues can ship"), the essay keeps its place in the catalog at the next free number, 394. Content is unchanged from the original draft; the edits are renumber-only.
Contents
Agent independence discipline (
17135fb,fb6b574)INDEPENDENCE.md— the governing doc: the one test, the five independence sources, the autocorrelation trap, the Mechanical/Judgment taxonomy, the mandatoryIndependence sourceheader, and the kbot-BYOK heterogeneity policy.japanese-editor.mdrewritten as the worked example (evidence-grounded, escalates-to-human, PASS-TO-HUMAN verdict).Independence sourceheader rolled out across the agent roster.ISSUE 394 — THE DESK THAT SURVIVES (
290d189, was 392)ISSUE_392→ISSUE_394,number '392'→'394', dateline bumped MAY→JUNE /V·26→VI·26to sit with the 392/393 June run, back-cover image →public/back-covers/394-desk.jpg, attribution + header comments renumbered.〜の用, also in 369) staged for a native human.Editorial note
394 is appended to
ALL_ISSUES, so it becomesLATEST_ISSUEand drives the landing cover, displacing 393 (OWN THE STACK). 392/393 are a paired set; 394 reads as a craft palate-cleanser after them. If 393 should remain the cover, re-orderALL_ISSUES.Verification
npm run build(tsc && vite build) green, exit 0.https://claude.ai/code/session_01X23jYno1eGJ1o9kn1Sum8x