- 55comments
- —discuss
- 41comments
- 30comments
- 224comments
- —discuss
- 335comments
- 16comments
- 181comments
- 317comments
- 9comments
- 83comments
- 37comments
- 331comments
- 271comments
- 182comments
- 133comments
- 113comments
- 6comments
- 152comments
- 76comments
- 195comments
- 28comments
- 144comments
- —discuss
- 271comments
- 43comments
- 24comments
- 73comments
- 5comments
Looks like a well engineered, automated abliteration pipeline. The claims seem a bit overstated though, since the metrics mentioned are cherrypicking refusal count and KL divergence, both of which make the outcome seem the most dramatic.
I personally never saw much of a quality drop from models put through Heretic if that amounts to anything. They have been working quite well on small local models so far.
Can the load-bearing gaps that are worth being flagged for pinning down be abliterated out of a model?
Keep a close eye on abliterated and "heretic" open weight models. They will be outlawed first.
I'm not sure what is your point. It reads as defeatism to me but I'm not sure.
Could you elaborate? Do you find it good or bad? What actions can be taken?
Hes of the mind that american fascism will hold together long enough to be competent decesion makers