Latest / Logosofia no Dia a Dia
Abliteration: How $5 Undoes a Model's Guardrails
Open-weight models ship with safety training baked in, and thousands of people quietly take it back out. This episode traces the technical arc from a single paper finding that refusal lives in one direction of activation space, through a $5 rank-one weight edit, to Heretic — an AGPL tool with 34,000 GitHub stars that automates the whole process and outperforms skilled human operators. Along the way: the split between quantization (an access problem) and behavior modification (a different animal entirely), why permissive licenses mean the most interesting fine-tunes never get published, and a…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.