Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- A flawless distillation.by dude250711
- Someone tell me if I'm overreacting, but does the ability to abliterate guardrails basically mean that alignment is basically a lost cause?by qgin
- Anyone with a multi-GPU cluster at home that has given it a try?by pgsandstrom
- I do not like these "surgical removals" and would rather prefer a pass over from a tool like Heretic. These surgical removals often trigger and analyze the activated neurons and erase them. This worked fine on older models where a single refusal vector existed. Now these "abliterated" models all suffer from catastrophic breakage because they are not as simple anymore. HauhauCS (on HF) for example, makes great uncensored models although they often work on smaller models rather than large ones like this.by tacomagick
- Most of what these models gate is stuff you can find with a library card. The safety filter is more about liability than actual prevention.by pullstart
- I've seen some people complain about the work of dealign.ai and similar groups, but personally, I fully support it. If LLMs have a lasting effect on society, I'd prefer to see some options that don't have generic corpo-speak anti-liability status quo guards encoded into them by default.by crooked-v