2026-10-20 12:06 UTC
Replies (3)
-
@swlabr@awful.systems 2026-10-20 12:15
wiktionary claims it is a blend of “ablate” and “obliterate”, it does not list an origin (at this point in time)
-
@zogwarg@awful.systems 2026-10-20 12:51
With a bit of google searching by date it seems like this guy (huggingface.co/…/Meta-Llama-3-70B-Instruct-ablite…) claims ownership of the coining, which I find plausible, based on the list of released weights and their timing. As far as “abliteration”: it’s just a fun play-on-words using the original “ablation” term used in the original paper to refer to removing features, which I made up particularly to differentiate the model from “uncensored” fine-tunes. Ablate + obliterated = Abliterated. The paper being referred to being: Refusal in Language Models Is Mediated by a Single Direction which seems to have somehow started out on the “AI alignement forum” of LessWrong alignmentforum.org/…/refusal-in-llms-is-mediated-… first posted 27th April. In general it’s a method of weight alteration so only really applicable to some opensource (or i guess leaked) models. First model with abliterated in the name by “failspy” on May 8th.
-
@istewart@awful.systems 2026-10-21 00:32
Sounds like a marketing tagline for a failed “As Seen on TV” sort of gadget, tbh