task-observer: docs/ai/writing-docs updates from 2026-06-17#57
Open
divad12 wants to merge 1 commit into
Open
Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Target\nglobal-doc: docs/ai/writing-docs.md\n\n## Observations addressed\n- Observation 1 (dotfiles/log.md): Compression can weaken corrective guardrails → changed: added bullet "When compressing instructions, remove redundancy without reducing enforcement force. Imperative wording and explicit fallback paths guard against known failure modes; preserve them even when shortening for context budget."\n- Observation 2 (dotfiles/log.md): Explain why guardrails exist when model behavior depends on it → changed: added bullet "Keep compact rationale for judgment-heavy rules. A model must generalize the rule to unlisted cases; without the why, it satisfies only the literal surface form."\n- Observation 3 (dotfiles/log.md): Code guardrails need failure-mode rationale → changed: added bullet "Keep failure-mode rationale alongside safety-critical rules. Name the required behavior and what goes wrong otherwise. Bare imperatives are easier to rationalize around than imperatives paired with a concrete failure description."\n- Observation 4 (dotfiles/log.md): Positive phrasing is better for tradeoff guidance → already partially addressed by the existing "Lead with the positive action" bullet; no additional change needed.
Generated by Claude Code