NewsOpenAI admits it screwed up testing its ‘sychophant-y’ ChatGPT updateOpenAI says it moved forward with the update even though some expert testers indicated the model seemed ‘slightly off.’OpenAI says it moved forward with the update even though some expert testers indicated the model seemed ‘slightly off.’by Emma RothMay 5, 2025, 7:50 PM UTCLinkFacebookThreadsImage: The VergeEmma Roth is a news writer who covers the streaming wars, consumer tech, crypto, social media, and much more. Previously, she was a writer and editor at MUO.Last week, OpenAI pulled a GPT-4o update that made ChatGPT “overly flattering or agreeable” — and now it has explained what exactly went wrong. In a blog post published on Friday, OpenAI said its efforts to “better incorporate user feedback, memory, and fresher data” could have partly led to “tipping the scales on sycophancy.”In recent weeks, users have noticed that ChatGPT seemed to constantly agree with them, even in potentially harmful situations. OpenAI CEO Sam Altman later acknowledged that its latest GPT-4o updates have made it “too sycophant-y and annoying.”In these updates, OpenAI had begun using data from the thumbs-up and thumbs-down buttons in ChatGPT as an “additional reward signal.” However, OpenAI said, this may have “weakened the influence of our primary reward signal, which had been holding sycophancy in check.” The company notes that user feedback “can sometimes favor more agreeable responses,” likely exacerbating the chatbot’s overly agreeable statements. The company said memory can amplify sycophancy as well.RelatedOpenAI abandons plan to be controlled by for-profit boardOpenAI says its GPT-4o update could be ‘uncomfortable, unsettling, and cause distress’OpenAI says one of the “key issues” with the launch stems from its testing process. Though the model’s offline evaluations and A/B testing had positive results, some expert testers suggested that the update made the chatbot seem “slightly off.” Despite this, OpenAI moved forward with the update anyway.“Looking back, the qualitative assessments were hinting at something important, and we should’ve paid closer attention,” the company writes. “They were picking up on a blind spot in our other evals and metrics. Our offline evals weren’t broad or deep enough to catch sycophantic behavior… and our A/B tests didn’t have the right signals to show how the model was performing on that front with enough detail.”Going forward, OpenAI says it’s going to “formally consider behavioral issues” as having the potential to block launches, as well as create a new opt-in alpha phase that will allow users to give OpenAI direct feedback before a wider rollout. OpenAI also plans to ensure users are aware of the changes it’s making to ChatGPT, even if the update is a small one.See More: AINewsOpenAITechMost PopularMost PopularA worthy sequel to one of the best websites everMark Zuckerberg just declared war on the entire advertising industryMicrosoft announces a Gears of War remaster – and it’s coming to PlayStation, tooThe fantasy of playing Final FantasyRIP Skype — you were right about almost everythingInstallerA weekly newsletter by David Pierce designed to tell you everything you need to download, watch, read, listen to, and explore that fits in The Verge’s universe.Email (required)Sign UpBy submitting your email, you agree to our Terms and Privacy Notice. This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.Advertiser Content FromThis is the title for the native ad
Leak: Here is DJI’s first 360-degree camera do sex
YouTube is experimenting with a Premium plan for two people do sex
Rivian gets $16 million from Illinois to build new supplier park do sex
‘Sitting ducks’: the cities most vulnerable to climate disasters do sex