Skip to content

routine: curiosity-redirect-driven (2026-08-05) - #131

Draft
jim4226 wants to merge 1 commit into
mainfrom
claude/daily-2026-08-05-curiosity-redirect-driven
Draft

routine: curiosity-redirect-driven (2026-08-05)#131
jim4226 wants to merge 1 commit into
mainfrom
claude/daily-2026-08-05-curiosity-redirect-driven

Conversation

@jim4226

@jim4226 jim4226 commented Aug 5, 2026

Copy link
Copy Markdown
Owner

Summary

Adds a "redirect-driven" escalation to Curiosity: after a frontier item rolls back twice in a row on the same root item, the follow-up queue stops reissuing the identical re-investigate '...' prompt and instead emits a broader redirect: '...' kept failing ...; broaden scope instead of retrying the same fix item. A promotion on that root clears its failure streak.

Source: https://www.anthropic.com/research/discovering-cryptographic-weaknesses (Frontier Red Team, published 2026-07-28) — "Discovering cryptographic weaknesses with Claude." Quote: "when initial attempts fail, strategic prompting redirects the agent away from 'low hanging fruit' toward deeper exploration."

Theme: 7 — Curiosity / frontier-item generation (exploration policies, novelty detection, automated red-teaming).

Touches: csis/curiosity.py (Curiosity.record_rollback / record_promoted / next), tests/test_daemon.py.

Size: small (~90 LOC incl. tests). Risk: low — does not touch any cycle-9 chokepoint (Coordinator.__init__, _BackendTracker, writer_iteration_id, promotion CAS); purely additive to the frontier-item source rotation the daemon already consumes through the unchanged next()/record_rollback()/record_promoted() interface.

Test plan

python -m pytest tests/test_daemon.py -q
python -m pytest tests/ -q

Both pass locally (252 passed, including 2 new regression tests: test_curiosity_redirects_after_repeated_failure_on_same_root and test_curiosity_record_promoted_clears_failure_streak).


Generated by Claude Code

A frontier item that rolls back twice on the same root re-investigate
prompt now escalates to a redirect-driven follow-up instead of reissuing
the identical retry a third time. Mirrors the exploration pattern from
Anthropic's Frontier Red Team cryptographic-weakness research: when a
narrow attempt doesn't work, redirect toward broader/deeper exploration
rather than repeating it verbatim.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Rdk9Wn6QAJwjEpG9ZwJFjL
@jim4226 jim4226 mentioned this pull request Aug 5, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants