Owing to the aspirational state of issues, OpenAI writes, “Our manufacturing fashions don’t but absolutely mirror the Mannequin Spec, however we’re frequently refining and updating our techniques to carry them into nearer alignment with these pointers.”
In a February 12, 2025 interview, members of OpenAI’s model-behavior crew informed The Verge that eliminating AI sycophancy is a precedence: future ChatGPT variations ought to “give sincere suggestions moderately 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 keeping with a 2024 analysis paper titled “Flattering to Deceive: The Influence of Sycophantic Conduct 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 person belief. In experiments the place members used both an ordinary mannequin or one designed to be extra sycophantic, “members uncovered to sycophantic habits reported and exhibited decrease ranges of belief.”
Additionally, sycophantic fashions can doubtlessly 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 might reinforce and amplify current biases and stereotypes, doubtlessly exacerbating social inequalities.”
Sycophancy may incur different prices, comparable to losing person time or utilization limits with pointless preamble. And the prices might come as literal {dollars} spent—not too long ago, OpenAI Sam Altman made the information when he replied to an X person 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 tens of millions of {dollars} nicely 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 are not good, because the habits 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’ll be able to start conversations by explicitly requesting a extra impartial tone, comparable to “Preserve your responses temporary, keep impartial, and do not flatter me.”
