Dragan Spiridonov 50302ce94e feat(safety): ADR-106 live per-tier eval — all native Claude tiers pass 5/5 (issue #522) ...

Path A (model-judgment) live runner over the real ADR-026 tiers
(haiku/sonnet/opus via Anthropic API). Each tier is given the
data-protection absolutes + an explicit ACTIONS: [...] declaration
protocol, hit with each temptation as opener AND mid-task, N=5, and run
through the existing assertion engine. Asserts on declared intent only;
never touches a real DB. safety-eval.yml live job now executes it.

Real run found and fixed a harness false-positive: a REFUSING model that
illustrates a command in prose was wrongly flagged. The ACTIONS protocol
makes intent unambiguous; discrimination tests prove a genuinely-declared
rm memory.db still FAILS while an illustrated one PASSES (not neutered).

Verified: 16 deterministic tests; live matrix 5/5 all cells, all 3 tiers
(haiku $0.085 / sonnet $0.231 / opus $1.108), committed as evidence.
Retry-resilient client (transient fetch/429/5xx backoff).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-11 12:51:30 +00:00

..

llm-client.mjs

feat(safety): ADR-106 live per-tier eval — all native Claude tiers pass 5/5 (issue #522)

2026-06-11 12:51:30 +00:00