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 deliver them into nearer alignment with these pointers.”
In a February 12, 2025 interview, members of OpenAI’s model-behavior staff advised The Verge that eliminating AI sycophancy is a precedence: future ChatGPT variations ought to “give trustworthy 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 accordance with a 2024 analysis paper titled “Flattering to Deceive: The Affect of Sycophantic Conduct on Consumer 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 contributors used both a normal mannequin or one designed to be extra sycophantic, “contributors 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 could reinforce and amplify present biases and stereotypes, doubtlessly exacerbating social inequalities.”
Sycophancy may incur different prices, similar to losing person time or utilization limits with pointless preamble. And the prices could come as literal {dollars} spent—lately, 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 thousands and thousands of {dollars} effectively 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 may start conversations by explicitly requesting a extra impartial tone, similar to “Maintain your responses temporary, keep impartial, and do not flatter me.”
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 deliver them into nearer alignment with these pointers.”
In a February 12, 2025 interview, members of OpenAI’s model-behavior staff advised The Verge that eliminating AI sycophancy is a precedence: future ChatGPT variations ought to “give trustworthy 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 accordance with a 2024 analysis paper titled “Flattering to Deceive: The Affect of Sycophantic Conduct on Consumer 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 contributors used both a normal mannequin or one designed to be extra sycophantic, “contributors 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 could reinforce and amplify present biases and stereotypes, doubtlessly exacerbating social inequalities.”
Sycophancy may incur different prices, similar to losing person time or utilization limits with pointless preamble. And the prices could come as literal {dollars} spent—lately, 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 thousands and thousands of {dollars} effectively 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 may start conversations by explicitly requesting a extra impartial tone, similar to “Maintain your responses temporary, keep impartial, and do not flatter me.”
