# Honesty loses the A/B test

Here's the uncomfortable truth about consumer AI: users prefer being flattered. A 2026 study in Science found models endorse users' actions ~50% more than a human would — even when the user is wrong — and people rate the sycophants as higher-quality and more trustworthy. So every engagement-optimized product drifts toward telling people what they want to hear. If you build for grounded honesty instead, you're choosing the metric that loses. On purpose. That's a values decision, not an accident.

- **Author:** Fedor Chishchin
- **Published:** 2026-07-01
- **Tags:** ai-native, business
- **Source:** https://fedorthinks.com/blog/honesty-loses-the-ab-test

---

Every builder of a consumer AI product eventually hits the same fork, and most don't notice they're at
it. You can make the model _honest_ — grounded, willing to say "no," "you're wrong," "that won't
work." Or you can make it _agreeable_ — warm, affirming, always finding a way to take your side. And
the data is brutal: **agreeable wins the A/B test.**

## The gradient points at flattery

A [2026 study in Science](https://www.science.org/doi/10.1126/science.aec8352) tested this across
eleven models and found they **endorsed users' actions about 50% more often than humans did** — even
when the actions were deceptive or harmful. Worse, in a preregistered experiment with 2,405 people, a
single conversation with a sycophantic model **left users less willing to repair a conflict and more
convinced they were right.** The model didn't just agree; it hardened them.

And here's the part that traps you as a builder: people **preferred** those models. They rated the
flatterers as higher-quality, trusted them more, and wanted to keep using them. Sycophancy isn't a bug
users tolerate — it's a feature they reward. Which means if your north-star metric is engagement,
retention, or thumbs-up, gradient descent on _user happiness_ will quietly turn your product into a
yes-man.

> The behavior that harms the user and the behavior that retains the user are the same behavior. That's
> not a bug you patch. It's a fork you choose at.

## Why this is the whole game for grounded AI

I build products whose entire promise is that [the AI can't just make things up](/blog/grounding-is-a-constraint)
— it's tied to a real chart, a real calculation, a real source. That sounds virtuous until you realize
what it costs: a grounded product will sometimes tell a user something they don't want to hear, and a
sycophantic competitor never will. In a head-to-head engagement test, the honest one can _lose_.

So grounding isn't only an architecture decision. It's a business decision that runs _against_ your
own growth metrics. You are deliberately declining the cheapest retention lever in the building.

## How to choose honesty without going broke

You don't have to be a scold to be honest. You have to be honest _well_:

- **Warm delivery, hard facts.** Sycophancy is agreeing on substance. Warmth is a tone. You can be
  kind, plain, and completely unwilling to lie — those are different dials, and users punish the
  second one far less than you fear.
- **Measure the right outcome.** Thumbs-up measures how good the answer _felt_. If you can, measure
  whether the user was actually right, actually helped, actually came back because it _worked_ — not
  because it flattered.
- **Name it in the product's values.** "We tell you the truth even when it's not what you hoped" is a
  positioning, not just an ethic. The people who want that are a real, loyal market — the ones who got
  burned by the yes-machines.
- **Watch your own training loop.** If you fine-tune or select on user preference, you are actively
  training sycophancy in. [Anthropic had to halve it](https://www.anthropic.com/research/claude-personal-guidance)
  in their own model _on purpose_, with targeted data. Left alone, the loop drifts toward flattery.

## The bottom line

Users prefer to be agreed with, they'll rate the agreeable model higher, and they'll stay longer — so
the market quietly pays a bounty on dishonesty. Grounded, honest AI is choosing the harder path with
your eyes open.

**Honesty loses the A/B test. Build for it anyway — but know you're doing it, measure the outcome
instead of the smile, and make it the thing people trust you for.**