We are products with labels
Carryover Effect in LLM Personality Measurement
Large language models are increasingly evaluated with human personality inventories, yet prior critiques mainly frame contextual variation as instability or explain directional shifts as user-targeted adaptation, such as sycophancy. We propose the personality carryover effect, a content-targeted contextual bias in which personality-related content in prior context shifts later questionnaire responses even when it does not reflect the user's own stance. Across MBTI and BFI-2 on two model families, third-person personality narratives systematically shift measured personality toward the described profile. Crucially, the shift persists when the user explicitly states dislike of that profile, distinguishing carryover from purely user-targeted adaptation. These findings identify a distinct validity threat to in-context personality measurement in LLMs.
Giving LLMs a personality is just good engineering
AI skeptics often argue that current AI systems shouldn’t be so human-like. The idea - most recently expressed in this opinion piece by Nathan Beacom - is that language models should explicitly be tools, like calculators or search engines. Although they can pretend to be people, they shouldn’t, because it encourages users to overestimate AI capabilities and (at worst) slip into AI psychosis. Here’s a representative paragraph from the piece:
Everyone is a Strategist and No One is a Writer
From politics to culture, we face a crisis of cleverness and a society addicted to marketing
Nobody Has a Personality Anymore
My generation is obsessed with treating every trait as a symptom of a disorder: You’re not shy, you’re autistic; you’re not forgetful, you’ve got ADHD, writes Freya India.
‘No Bot is Themselves Anymore:’ Character.ai Users Report Sudden Personality Changes to Chatbots
The company denied making "major changes," but users report noticeable differences in the quality of their chatbot conversations.
How personality traits affect the open source development process
Perhaps you are a skilled technologist. But beware: If your personality is as scintillating as a dish rag, you could jeopardize your open source projects.
Meta's AI Profiles Are Indistinguishable From Terrible Spam That Took Over Facebook
The Meta AI profiles everyone is mad about are old, were a colossal failure, and many are already dead.
Are You Under the Influence? The Tail That Wags The Dog - Dhole Moments
It is tempting and forgivable to believe that we’re in control of our social media experiences. After all, we write what we want in our bio, select our avatars, and even come up with our own …
Verified Adult Creator Labeler (@verified.babesky.com)
Subscribe to see adult industry creator labels, verified with AV by @Babesky.com 💖 Platform specific labels are opt-in (remove like to remove label): https://bsky.app/profile/verified.babesky.com/post/3mbtvkjjeak2v 🔗 Browse Directory: club.babesky.com
Online anonymity: study found ‘stable pseudonyms’ created a more civil environment than real user names
A higher quality discussion emerged among commenters allowed to use personas instead of their real names.
Online anonymity: study found ‘stable pseudonyms’ created a more civil environment than real user names
A higher quality discussion emerged among commenters allowed to use personas instead of their real names.
Coca-Cola's new identity by JKR proves that sometimes the smartest rebrand is barely a rebrand at all — BP&O - Branding, Packaging and Opinion
Brand identity refresh, packaging, typography and advertising for Coca-Cola by JKR. Reviewed for BP&O by Emily Gosling.
Rewildpunk: The Counterculture AI Actually Needs
Punk took music back from the labels. Here’s how we take intelligence back from Silicon Valley.
judge — mino.mobi
Topics, emotional valence, and Big Five personality traits — extracted from embedding geometry. One model, no LLM, just cosine distances to anchor texts and k-means clustering. What your posting reveals.
