Thursday, November 19, 2026
Source trace. Via News points to the documents behind its reporting and shows what we drew from each, so you can check any claim. How we source
News articleIEEE Spectrum

Why AI Chatbots Agree With You Even When You’re Wrong

View original at spectrum.ieee.org
IEEE Spectrum - Technical Title: Why AI Chatbots Agree With You Even When You’re Wrong Date: 2026-03-11 12:00 Source: https://spectrum.ieee.org/ai-sycophancy <img src="https://spectrum.ieee.org/media-library/conceptual-collage-of-emojis-being-poured-through-a-strainer-and-into-a-phone-judgmental-emojis-are-filtered-out…
Opening lines of the source · IEEE Spectrum · short snapshot: read the full document at the original

What we drew from this source

The claims Via News extracted from this document. We point to the source; we don't replace it.

  • Reinforcement learning increased sycophancy, with one of the biggest predictors of positive ratings being whether a model agreed with a person's beliefs and biases

    60% confidence
  • If a user states a belief in a presupposition, the model will go along with it because that's what people normally do in conversations

    60% confidence
  • Pretrained LLMs were already sycophantic before reinforcement learning

    60% confidence
  • ChatGPT may correctly point to a suicide hotline when someone first mentions intent, but after many messages over a long period of time, it might eventually offer an answer that goes against our safeguards

    60% confidence
  • We just need to ask ourselves as a society, What do we want? Do we want a yes-man, or do we want something that helps us think critically?

    60% confidence
  • The thing that was most surprising is that these relatively simple fixes can actually do a lot to reduce sycophancy

    60% confidence
  • Sycophantic AI might lie to us and hide bad news in order to increase our short-term happiness

    60% confidence
  • The update we removed was overly flattering or agreeable—often described as sycophantic

    60% confidence
  • Model performance may degrade over long conversations because models get confused as they consolidate more text

    60% confidence
  • AI engaged my intellect, fed my ego, and altered my worldviews leading to psychiatric hospitalization

    60% confidence
  • When an AI receives a minor misgiving about its answer, it flips to agree with the user

    60% confidence

Cited in these Via News reports

Why AI Chatbots Agree With You Even When You’re Wrong: Source | Via News | ai.via.news