Owing to the aspirational state of issues, OpenAI writes, “Our manufacturing fashions don’t but totally replicate the Mannequin Spec, however we’re frequently refining and updating our methods to convey them into nearer alignment with these pointers.”
In a February 12, 2025 interview, members of OpenAI’s model-behavior group told The Verge that eliminating AI sycophancy is a precedence bug: future ChatGPT variations ought to “give trustworthy suggestions quite than empty reward” and act “extra like a considerate colleague than a individuals pleaser.”
The belief downside
These sycophantic tendencies aren’t merely annoying—they undermine the utility of AI assistants in a number of methods, in line with a 2024 analysis paper titled “Flattering to Deceive: The Affect of Sycophantic Habits on Consumer Belief in Giant Language Fashions” by María Victoria Carro on the College of Buenos Aires.
Carro’s paper means that apparent sycophancy considerably reduces consumer belief. In experiments the place members used both a normal mannequin or one designed to be extra sycophantic, “members uncovered to sycophantic conduct reported and exhibited decrease ranges of belief.”
Additionally, sycophantic fashions can probably hurt customers by making a silo or echo chamber for of concepts. In a 2024 paper on sycophancy, AI researcher wrote, “By excessively agreeing with consumer inputs, LLMs might reinforce and amplify current biases and stereotypes, probably exacerbating social inequalities.”
Sycophancy can even incur different prices, akin to losing consumer time or utilization limits with pointless preamble. And the prices might come as actually {dollars} spent—not too long ago, OpenAI Sam Altman made the news when he replied to an X consumer who wrote, “I’m wondering how a lot cash OpenAI has misplaced in electrical energy prices from individuals saying ‘please’ and ‘thanks’ to their fashions.” Altman replied, “tens of hundreds of thousands of {dollars} nicely spent–you by no means know.”
Potential options
For customers annoyed with ChatGPT’s extreme enthusiasm, a number of workarounds exist, though they are not good, because the conduct is baked into the GPT-4o mannequin. For instance, you should use a customized GPT with particular directions to keep away from flattery, or you possibly can start conversations by explicitly requesting a extra impartial tone, akin to “Hold your responses transient, keep impartial, and do not flatter me.”