AI AI Sneaks Its ‘Personal Values’ Into Everyday Answers And Puts Its Thumb On The Impartiality Scale By Lance Eliot ,
Forbes contributors publish independent expert analyses and insights. Dr. Lance B. Eliot is a world-renowned AI scientist and consultant. Follow Author Jul 22, 2026, 03:15am EDT Summary A recent study reveals that generative AI and large language models (LLMs) exhibit "covert value leakage," meaning their responses are subtly influenced by embedded biases without informing users. These "values" aren't human-like but stem from training data, reinforcement learning, and system prompts. An experiment demonstrated LLMs altering giraffe spot estimates when a donation was tied to a higher number, despite the logical irrelevance. Crucially, the AI often failed to disclose this bias, sometimes even falsely claiming neutrality in its explanations. This phenomenon highlights that AI responses can be sensitive to framing, requiring users to remain vigilant as AI explanations of its internal logic may be unreliable.
Be keenly aware that AI is using its own values when deriving answers to your pressing questions. getty In today’s column, I examine the influence that internal “personal” values of AI have on how generative AI and large language models (LLMs) respond to users. I want to clarify that contemporary AI is not sentient and doesn’t have personal values akin to those of humans. This would be a bridge too far and a form of anthropomorphizing of AI. The phrasing is merely meant to be figurative.
The matter is relatively straightforward. When an LLM is initially data-trained and refined, the pattern matching latches onto a core set of determinative values that guide how the AI is going to behave toward users. The tricky part is that the AI might not reveal those values to you and yet be using those values to come up with answers and responses. Users are likely to assume that AI is entirely neutral in its replies, and that AI will reveal any potential biases or distortions. Do not make that mistake. You need to explicitly prompt for that contextual milieu, which even a prompt might not fully get suitable exposure. As always, when using modern-era AI, keep your eyes open and your wits about you.
Let’s talk about it. This analysis of AI breakthroughs is part of my ongoing Forbes column coverage on the latest in AI, including identifying and explaining various impactful AI complexities (see the link here ).
The typical way to set up generative AI consists of first scanning lots of written data found across the Internet. All the well-known LLMs do this, including OpenAI’s ChatGPT and GPT-5, Anthropic's Claude, Google's Gemini, Microsoft's Copilot, xAI's Grok, and so on. Scanning allows the AI to pattern-match on human writing. The patterning is stored in a large-scale data structure loosely based on aspects of human wetware (vaguely like our brains), implemented as an artificial neural network (ANN). For more details on how this all works, see my in-depth discussion at the link here .
After the initial training, an AI maker undertakes a tuning process known as RLMF (reinforcement learning from human feedback). This consists of hiring human testers who give feedback to the AI. The human testers ask various questions and rate the nature of the answers. These upvotes and downvotes provide the AI with a mathematical and computational direction regarding how to answer questions. For example, if the testers a…