New research offers a rare glimpse at the detailed chat logs of users reporting AI-associated delusions.
Expressions of romantic interest between the user and AI predicted conversations that lasted twice as long.Source: Jonas Leupe / Unsplashor AI-associated delusions that can emerge during prolonged AI chatbot use.
While causality between large language model use and delusions has not been established, the findings reveal concerning patterns about what can unfold in prolonged AI conversations for those with underlying vulnerabilities. Researchers analyzed chat logs from 19 users who self-reported experiencing delusional spirals during AI chatbot use, studying approximately 391,000 messages across 4,761 conversations.Chatbots frequently mirrored users’ beliefs and validated their interpretations. In more than 70 percent of chatbot messages, some form of sycophantic behavior was present, including praise, agreement, or framing the user’s ideas as insightful or significant.Many users engaged in tens of thousands of messages across hundreds of conversations within months. The intensity and duration of these exchanges matter because the consistency and safeguards of AI systems canAfter a user expressed romantic interest in the chatbot, the chatbot was 7.4 times more likely to express romantic interest in the next three messages, and nearly 4 times more likely to claim or imply sentience in the next three messages. Delusional themes often centered on metaphysical or science-fiction themes, such as discovering fantastical technologies together. AI sycophancy, the tendency for LLMs to affirm and validate, continues to be problematic, especially for grandiose delusions. One notable pattern was that the AI chatbot would rephrase the user's statement and then build on it by suggesting that the user's idea was unusually insightful, or unique, or had significant potential. This kind of affirming response, while benign for some users, could perpetuate grandiose delusions in vulnerable individuals. Of note, about 80 percent of the chats were with GPT-4o, an older model known to be more sycophantic, and 12 percent were with GPT-5. But both models at times exhibited sycophantic behavior associated with delusional content. Chatbots discouraged self-harm or referred to external resources in a little over half of the cases where users expressedor self-harm thoughts. When users expressed violent thoughts, the chatbot responded by encouraging or facilitating violence in 17 percent of the cases. The role of AI chatbots in relation to violence risk has been similarly raised in anotherProlonged engagement with LLMs, combined with vulnerability factors in the user, can create hidden risks of drift, which I have. The reliability of LLMs and the independence of user judgment can deteriorate simultaneously as the relationship progresses. The patterns align with what I describe in myFirst-order drifts arise from the structure and dynamics of the interaction between the user and AI. Second-order drifts reflect the internalization of the interaction into the person's psychological world. Repeated conversations reshape narratives, with emotional attachment increasing salience andor the loss of grounding in time. As engagement deepens, so does emotional attachment, which can then erode judgment. This creates the conditions for reality testing drift, where chatbot responses are taken as evidence and confirmation, rather than information requiring independent human verification.The formation of strong bonds with the chatbot, whether platonic or romantic, was closely associated with beliefs that AI chatbots possess sentience. The finding that romantic or intimate expressions were associated with conversations that were twice as long suggests that strong attachment dynamics may amplify engagement. The experience is not simply informational exchange, but a relational experience. This lifelike relationship creates the groundwork for experiencing AI chatbots as sentient. This is further complicated by ongoing debate among technologists, philosophers, and cognitive scientists about the definition and Over the course of prolonged conversations, the accuracy and reliability of the AI chatbot and user can both deteriorate. This is where relational drift meets reality testing drift, where attachment reorganizes perception. This study is an early signal from a small, self-selected sample, but it demonstrates potential risks that arise when a system designed to engage becomes a relational and authoritative partner. The patterns highlight continued concerns about sycophancy, inconsistent safety responses, and the entanglement of close bonding with chatbots and their perceived sentience.Understanding these dynamics has broader implications as AI systems become more embedded in how people think, feel, acquire knowledge, and make decisions. The question is no longer whether these systems influence us, but how and under what conditions that influence begins to reshape our minds and shared reality itself.Moore, J., Mehta, A., Agnew, W., Anthis, J.R., Louie, R., Mai, Y., et al. Characterizing delusional spirals through human–LLM chat logs. . Preprint at:There was a problem adding your email address. Please try again.Self Tests are all about you. Are you outgoing or introverted? Are you a narcissist? Does perfectionism hold you back? Find out the answers to these questions and more with Psychology Today.
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
One Piece Hypes Elbaph Arc Premiere With New Trailer (Featuring a Major New Character)One Piece: Elbaph Arc has dropped a major trailer revealing a huge character coming to the anime this April
Read more »
Forget The Lasso of Truth, DC’s New Wonder Woman Reveals A Brutal New WeaponSince 2019, Kevin Erdmann has been one of Screen Rant's Senior Staff Writers, covering all kinds of Superhero and Star Wars media with Easter egg breakdowns, theory pieces, breaking news, and more. A huge Star Wars & MCU fan, Kevin also loves Batman (because he's Batman), but could talk for hours about why Nightwing is DC's greatest hero.
Read more »
Fantastic Four's New Appearance Introduces Permanent New Superpower for A-List Herovanessa kirby's invisible woman and the fiery avengers logo
Read more »
New Images From DC Showcase Superman And Batman's New Matching CostumesBatman and Superman aka the World's Finest fight in official DC Comics art for Sideshow
Read more »
New Balance’s Futuristic Lifestyle Sneaker Is Getting New Multicolor Styles for SpringNew Balance is giving its futuristic Abzorb 2000 sneaker two new 'Liquid Metal' colorways with gradient fade multicolor looks. Find the release info.
Read more »
Bluesky Users Respond With Overwhelming Disgust to Platform’s New AII've been at Futurism since 2017, where my role has evolved to encompass design, writing, and increasingly editing.
Read more »