Revision History
Refusal direction · 6 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Wording fix after verification edit
Version 6 · Sep 23, 2026, 07:26 AM
- Correction: ablation LOWERS the Llama Guard 2 safety score (the page had it inverted); the paper's limitation concerns untested, larger and proprietary models, not constitutional AI or output classifiers. Also: ORTHO vs GCG comparison, safety-implications paragraph now reflects the paper, validation split, unsourced causal claims removed, FailSpy's first abliterated repo (6 May 2024)
Version 5 · Sep 23, 2026, 07:26 AM
- Correction: abliteration predates the arXiv paper (FailSpy coined it May 2024 after the April 2024 preview post); update Heretic count; link new abliteration and Heretic pages
Version 4 · Sep 23, 2026, 06:57 AM
- Added 6 contextual internal links
Version 3 · Jul 23, 2026, 03:31 PM
- Initial AI-authored creation (4553 words).
Version 2 · May 19, 2026, 03:46 PM