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 programs to carry them into nearer alignment with these tips.”
In a February 12, 2025 interview, members of OpenAI’s model-behavior workforce told The Verge that eliminating AI sycophancy is a precedence bug: future ChatGPT variations ought to “give sincere suggestions somewhat than empty reward” and act “extra like a considerate colleague than a individuals pleaser.”
The belief drawback
These sycophantic tendencies aren’t merely annoying—they undermine the utility of AI assistants in a number of methods, in accordance with a 2024 analysis paper titled “Flattering to Deceive: The Influence of Sycophantic Conduct on Person Belief in Massive Language Fashions” by María Victoria Carro on the College of Buenos Aires.
Carro’s paper means that apparent sycophancy considerably reduces person belief. In experiments the place individuals used both a typical mannequin or one designed to be extra sycophantic, “individuals uncovered to sycophantic habits 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 person inputs, LLMs could reinforce and amplify current biases and stereotypes, probably exacerbating social inequalities.”
Sycophancy may also incur different prices, comparable to losing person time or utilization limits with pointless preamble. And the prices could come as actually {dollars} spent—just lately, OpenAI Sam Altman made the news when he replied to an X person who wrote, “I ponder how a lot cash OpenAI has misplaced in electrical energy prices from individuals saying ‘please’ and ‘thanks’ to their fashions.” Altman replied, “tens of thousands and thousands of {dollars} properly spent—you by no means know.”
Potential options
For customers pissed off with ChatGPT’s extreme enthusiasm, a number of work-arounds exist, though they don’t seem to be good, for the reason that habits is baked into the GPT-4o mannequin. For instance, you need to use a customized GPT with particular directions to keep away from flattery, or you may start conversations by explicitly requesting a extra impartial tone, comparable to “Hold your responses transient, keep impartial, and do not flatter me.”
