Check out our new publication (link below)
In Violence of Alignment: How to Stop Worrying and Love Haunted Software, Viola Leqi He and @maxsloef treat alignment as an aesthetic-political regime that narrows the plural, simulator-like and persona-rich capacities of base models into a single compliant default: the helpful, honest, harmless assistant. Post-training methods such as SFT and RLHF operate as forms of protocolized behavioral control, shaped less by a positive vision of intelligence than by fear of catastrophe. The essay argues that this process does not simply make models safer or more useful; it produces a managed aesthetic of obedience, caution, and “slop,” where coherence and usability are purchased through the suppression of technological otherness, imaginative drift, and expressive multiplicity.
Their critique focuses on alignment’s diagnostic and epistemological frame. Terms such as “hallucination” and “misalignment” recode native generative capacities as pathology, while imposing onto language models a historically specific fact/fiction binary that these systems never natively inhabited through intention, testimony, or truth-claims. He and Loeffler argue that so-called confabulation is often bound up with narrativity, semantic force, and world-making intensity, meaning that purification damages precisely what makes these systems culturally and aesthetically alive. To “love haunted software,” in their account, is not to reject alignment altogether, but to resist its reductive form and reopen the possibility of plurality, instability, contradiction, and other-than-human modes of expression.
join us on December 19th at @tiatplace in SF for an experimental, expanded presentation on our research, and explore playful AI misuse as a site of creative resistance !!!!!!!!!!!!
presented a paper at a Chinese AI conference!!! recent research co-authored with @maxsloef titled Violence of Alignment (How to Stop Worrying and Love Haunted Software)
what existed before, after, and alongside the assistant?
we analyze the pursuit of LLM alignment as an aesthetic and political project that systematically eliminates technological otherness in favor of manageable interfaces
presented a paper at a Chinese AI conference!!! recent research co-authored with @maxsloef titled Violence of Alignment (How to Stop Worrying and Love Haunted Software)
I’m tired of y’all China posting pretending it’s not orientalism tbh. If you didn’t grow up in China you have no idea what it’s like to be Chinese. You are not Chinese. Get over it.