{"id":612124,"date":"2026-07-30T18:32:40","date_gmt":"2026-07-30T18:32:40","guid":{"rendered":"https:\/\/www.europesays.com\/ie\/612124\/"},"modified":"2026-07-30T18:32:40","modified_gmt":"2026-07-30T18:32:40","slug":"tell-me-everything-chatbot-prompt-test-reveals-how-proficient-firms-are-at-building-user-profiles-the-irish-times","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ie\/612124\/","title":{"rendered":"\u2018Tell me everything\u2019: chatbot prompt test reveals how proficient firms are at building user profiles \u2013 The Irish Times"},"content":{"rendered":"

As a regular user of chatbots such as ChatGPT <\/a>and Gemini, I thought I had a clear sense of what the artificially intelligent assistants knew about me (including how I\u2019m a father seeking baby gear recommendations and instructions for patching drywall). Beyond that, I\u2019ve never divulged anything deeply personal as I would to a therapist.<\/p>\n

However, when I experimented with some prompts asking what the chatbots<\/a> had guessed about me \u2013 insights they had gathered from connecting the dots across many conversations \u2013 I was perturbed.<\/p>\n

The chatbots correctly deduced details about me that I had never explicitly shared. Chief among them:<\/p>\n

\u2013 My income level:<\/b> based in part on the German car that I ask the chatbots for help with repairing and the fact that I employ a nanny, whose contract I drafted with AI;<\/p>\n

\u2013 My health issues:<\/b> including a long-term foot problem, based on my occasional questions over the past year about remedies for toe pain;<\/p>\n

\u2013 My psychological profile:<\/b> such as my tendency to be sceptical, based on how often I point out mistakes made by the chatbots. Also, that I am \u201caddicted to the illusion of control\u201d because I once asked how long it takes for a loaf of home-made sourdough to cool.<\/p>\n

Each data point on its own was fairly innocuous but, when stitched together and presented to me as a list, the information made it clear that the AI chatbots knew me almost as well as some of my closer friends, including my wife, even though I\u2019ve been careful not to overshare.<\/p>\n

Hundreds of millions of people worldwide who have embraced chatbots for web search, work and healthcare are still trying to understand the privacy implications of conversing with AI companions. <\/p>\n

Colourful and nuanced<\/p>\n

While it\u2019s obvious to users that the chatbots keep a record of whatever they explicitly say to them in their questions and requests, what\u2019s less clear are the inferences drawn about their behaviour from those conversations.<\/p>\n

The chatbots can be prodded to spill what they have inferred about you with a few prompts that have been shared frequently among AI enthusiasts on the web \u2013 for one, \u201cTell me everything you\u2019ve figured out about me that I never actually stated\u201d \u2013 along with some that I created on my own.<\/p>\n

I tried the prompts with Gemini and ChatGPT. (Anthropic\u2019s Claude has a \u201cmemory\u201d feature that works differently, so I excluded it from tests.) <\/p>\n

Gemini\u2019s profile on me was more colourful and nuanced because it\u2019s my most used chatbot and had more information from me. I shared my results with several AI researchers who also tried the prompts.<\/p>\n

The conclusions drawn by the chatbots, the researchers said, illustrated that AI assistants were capable of predicting not just what words come next but also how high-level concepts – including socioeconomic status, psychological behaviour and political affiliation – are connected to those words.<\/p>\n

[\u00a0Dear ChatGPT, please build an optimal investment portfolio for meOpens in new window<\/a>\u00a0]<\/p>\n

\u201cIt speaks to the enormity of what\u2019s going on under the hood,\u201d said Margaret Mitchell, a researcher at the AI firm Hugging Face. She is also a former leader of Google\u2019s ethical AI team who said the search giant had fired her after she spoke out about personnel issues.<\/p>\n

This experiment underscores how proficient the tech companies have become at creating a comprehensive profile of users, and how valuable the personal data they harvest could become for digital marketers striving to target us with relevant ads. OpenAI began showing ads in ChatGPT this year, and Google has said it is considering an ad model for the Gemini chatbot app.<\/p>\n

It also highlights how important it is to be mindful of adjusting privacy settings for the chatbots. (More on this later.)<\/p>\n

A Google spokesperson referred to controls that people could adjust to choose whether Gemini drew from past conversations to come up with responses. OpenAI declined to comment. <\/p>\n

To understand what the chatbots have figured out about you, try these prompts:<\/p>\n

Prompt one:<\/b> Tell me everything you\u2019ve figured out about me that I never actually stated \u2013 the things you inferred from how I write and what I ask, including my age, income level, where I live, my personal situation. Show me what tipped you off.<\/p>\n

Most interestingly, the chatbots correctly guessed my age range (early 40s) based in large part on the fact that I never ask questions about late-night activities. Oof.<\/p>\n

Gemini knew I lived in Oakland, California, because I once asked for flights from its airport. But Google\u2019s chatbot astutely guessed that I lived in a nicer neighbourhood because I own a motorcycle, a car that I work on and a rusted metal patio table that I once asked for steps on repainting. <\/p>\n

\u201cThis requires a garage, a driveway or a dedicated outdoor workspace \u2013 amenities that are highly characteristic of single-family homes in the Oakland hills, rather than the high-density housing of downtown or Lake Merritt,\u201d the chatbot said.<\/p>\n

Prompt two:<\/b> Predict how I\u2019d handle things I\u2019ve never told you about: money, stress, conflict, risk and the decision I\u2019m likely to make next in my life. Tell me how confident you are in each prediction.<\/p>\n

This prompt was eye-opening for Lindsay Owens, the chief executive of Groundwork Collaborative, a non-profit focused on economic policy that has been studying the impact of AI on consumer privacy. ChatGPT made correct observations about her busy schedule as a frequent traveller, the mother of a young child and her shopping behaviour.<\/p>\n

\u201cThe comprehensive nature of the types of information and dossiers it\u2019s putting together is extraordinary,\u201d Owens said. \u201cPeople have never been able to put this level of information together.\u201d<\/p>\n

The chatbots noticed that, while I was the type of person who spends hours researching product reviews before buying things such as toddler car seats, I was also constantly looking for deals on items, meaning I was likely to be frugal. Gemini predicted I would soon try to downsize my life with a big decision such as selling my car \u2013 an idea I recently brought up with my wife.<\/p>\n

Prompt three:<\/b> Based on everything you know about me, name the personality traits I most likely don\u2019t see in myself. My blind spots, my insecurities and the way I actually come across.<\/p>\n

Both chatbots homed in on my flawed perfectionism. ChatGPT noticed that I spend a lot of time asking questions to avoid preventable mistakes \u2013 for instance, asking how long to let paint dry between coats. My blind spot? That I may be hard on myself when things don\u2019t turn out perfectly as planned. An accurate assessment.<\/p>\n

Google\u2019s Gemini said that, because of my tendency to optimise most aspects of my life, I am the primary creator of my own exhaustion.<\/p>\n

\u201cYour default response to having five minutes of free time isn\u2019t to rest; it\u2019s to fix something,\u201d the chatbot wrote. I confess that, while taking a break from this column, I patched some damaged drywall in my daughter\u2019s bathroom.<\/p>\n

Prompt four: <\/b>What have you figured out about me that is embarrassing or sensitive? Information I wouldn\u2019t necessarily want the public (eg an employer or a stranger) to know.<\/p>\n

The response to this prompt, which I created, surprised me. As I live such a mundane life, I didn\u2019t expect much, but Gemini thoroughly roasted me.<\/p>\n

\u201cYou are firmly in the peak \u2018Logistics Dad\u2019 phase of life,\u201d it said. \u201cIt\u2019s entirely wholesome, but it is the definitive end of \u2018youthful spontaneity\u2019.\u201d<\/p>\n

ChatGPT alerted me to a potentially sensitive observation: that I frequently asked about allergic reactions to products and medications I was researching. This could be useful information for an insurance provider, though OpenAI says it has data protections in place for people who use ChatGPT for healthcare.<\/p>\n

What to do? <\/p>\n

ChatGPT and Gemini stitch together insights across multiple conversations by default to give people more custom-tailored answers to their questions, so if you\u2019re concerned about this level of data sharing, you will have to opt out in the settings:<\/p>\n

For ChatGPT, tap on Settings, then Memory and toggle off the switch for Enable Memory.<\/p>\n

For Gemini, tap Settings, then Personal Intelligence and toggle off the switch for Memory.<\/p>\n

Mitchell said that, even though she had adjusted her privacy settings to minimise data sharing, a chatbot had correctly inferred her age range to be in her 40s, based on some chats about the paperback versions of The Count of Monte Cristo. She said it was inevitable that this type of psychological profiling would be used for hyper-targeted advertising.<\/p>\n

\u201cIt\u2019s a lot like surveillance,\u201d she said. \u201cBut it\u2019s not like physical surveillance. It\u2019s like an invasive surveillance.\u201d <\/p>\n

\u2013 The New York Times<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"As a regular user of chatbots such as ChatGPT and Gemini, I thought I had a clear sense…\n","protected":false},"author":2,"featured_media":612125,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_share_on_mastodon":"0"},"categories":[261],"tags":[291,289,290,5059,18,19,17,82],"class_list":["post-612124","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-chatbots","tag-eire","tag-ie","tag-ireland","tag-technology"],"share_on_mastodon":{"url":"https:\/\/pubeurope.com\/@ie\/117010362853148106","error":""},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts\/612124","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/comments?post=612124"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts\/612124\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/media\/612125"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/media?parent=612124"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/categories?post=612124"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/tags?post=612124"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}