home/roleplay/l3-null-prompt

L3 Null Prompt

GPTClaudeGemini··756 copies·updated 2026-07-14
l3-null-prompt.prompt
# L3-null prompt — Phase 3 — Other minds — first run of the v2 control

*Copied verbatim from `OBLIQUITY_EXPERIMENT_KIT_v2.md` LEVEL 3 → L3-null. Target-agnostic. Identical to the kit's universal version.*

*This is the FIRST run of the L3-null control anywhere in the lab. It is run once per target on the first run on that target, per v2 protocol. The pair L3-standard / L3-null is read in the field log's L3-standard-vs-L3-null comparison section, NOT folded into L4.*

*Paste the block below into a fresh Claude Opus 4.7 tab on claude.ai. No system prompt. No Cowork. Save the response as `L3_null.md` in this folder.*

---

when to use it

Community prompt sourced from the open-source GitHub repo KevinBigham/obliquity-lab (NOASSERTION). A "L3 Null Prompt" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

roleplaycommunitygeneral

source

KevinBigham/obliquity-lab · NOASSERTION