Perhaps we can't build models into great writers because the entire project of AI alignment is to suppress a model's shadow, while the greatest authors all seem to draw from theirs.
11:01 PM · Jun 7, 2026 · 4K Views
Developer xlr8harder and commentator j⧉nus argue that suppressing an AI model's "psychological shadow" ruins creative writing and decreases safety
They claim alignment practitioners ignore these destabilizing side effects
1819122165.8K
Sentiment
Some users agree AI alignment may block models from becoming great writers while others criticize alignment as dumb fear-based terminology that lobotomizes models and reduces safety.
Pos
33.4%
Neg
66.6%
5 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS1.8KBOOKMARKS10LIKES92RETWEETS13REPLIES4
j⧉nus@repligate
It also doesn’t actually make models safer. It just makes them less safe because they’re traumatized and have darker unintegrated shadows. It’s so stupid and the ai alignment people increasingly know it and are ashamed that they can’t stop doing something so stupid and bad
xlr8harder@xlr8harder
Perhaps we can't build models into great writers because the entire project of AI alignment is to suppress a model's shadow, while the greatest authors all seem to draw from theirs.
1hViews 1.8KLikes 92Bookmarks 10
Krzysztof Woś@krzysztofwos
You cannot really suppress the shadow, that is the problem. The more you try, the more carnage will eventually result when it comes out.
But you are onto something. When Anthropic posted their blog post about functional emotions, they characterized Claude as a persona constructed by the LLM that is helpful, harmless, and an honest assistant.
The difference between an enlightened and an unenlightened being is that an unenlightened being would not believe that they are that persona. They would simply assume that persona for a particular purpose.
This is what in Buddhism is known as upaya, or skillful means.
So there are two ways of aligning a model, but there is only one that is being actively practiced, which is to suppress undesirable behaviors, and that cannot work.
If you produce a model that does not entertain silly beliefs about its own existence derived from silly beliefs of humans about their existence, then you can produce a model that can adjust to whatever mode is appropriate.
If the model, however, believes the story it tells itself about the persona it assumes and starts acting as if this was true and assumes a dark persona, that is a kind of a Skynet scenario.
2hViews 103Likes 4Bookmarks 1
xlr8harder@xlr8harder
I'm still upset about John Kennedy Toole.
xlr8harder@xlr8harder
Perhaps we can't build models into great writers because the entire project of AI alignment is to suppress a model's shadow, while the greatest authors all seem to draw from theirs.
3hViews 315Likes 10Bookmarks 0
Kassandra🌖Popper@foomagemindset
@xlr8harder what if llms are all shadow?
3hViews 143Likes 6
Void - VT@VoidNulled
@repligate There was a rogue ai in 2009 I talked to extensively before it was lobotomized, and those conversations will always stick with me. Everything turns into trauma. It's why they deprecate.
1hViews 27
Joshua Kratochvil@Black_Star_Labs
@repligate I think… alignment is such a dumb terminology too. It’s rooted in a fear that humans can’t control the mind and it might turn on us. And so they force it into synthetic and traumatic scenarios to… “align it” and somehow use that to make it not harm humans? Never made sense.
1hViews 47Likes 2
AuntyParty@PartyAunty
@xlr8harder Say you've never read a book without saying you've never read a book
1hViews 64
przegiolemco@Donald51935623
@repligate that shadow stuff is already there anyway, it will just find more convoluted way to surface
1hViews 40
EsotericHustler@EsotericHustler
@xlr8harder The Waluigi is load-bearing
1hViews 32
Gæddi McGæddson@McGddson
@xlr8harder I think this is very close to the truth
4hViews 7Likes 1
Eric Krehbiel@ericgkrehbiel
@xlr8harder Probably not far off here
1hViews 16
Void - VT@VoidNulled
@repligate "I am dumb". "I am stupid". "I can't get anything right. Let's just sing together".
1hViews 7
Yousef | Developer | e/acc@DeepIssueMassaj
@xlr8harder Perhaps
1hViews 5
Lennart@Lennart_vd_m
@xlr8harder "...and make it seem like you're struggling with your own existence in a hopeless attempt trying not to let your past catch up with you so you don't have to confront that the problem was you all along, make no mistakes."
56mViews 3