OpenAI has explained exactly what went wrong after pulling a GPT-4o update that made ChatGPT “too sycophant-y and annoying.”
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 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.
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
OpenAI’s Sam Altman just announced release timing for GPT-5After promising OpenAI would stop the ramifications of its GPTs, the company's CEO announced GPT-5 release timing.
Read more »
OpenAI Shifts Focus With GPT-4.1, Prioritizes Coding And Cost EfficiencyThe release underscores the rapid iteration cycles in the AI space, demanding continuous evaluation of model capabilities, cost structures and alignment with business objectives.
Read more »
OpenAI’s New GPT 4.1 Models Excel at CodingGPT 4.1, GPT 4.1 Mini, and GPT 4.1 Nano are all available now—and will help OpenAI compete with Google and Anthropic.
Read more »
OpenAI debuts its GPT-4.1 flagship AI modelOpenAI has introduced GPT-4.1, a successor to the GPT-4o multimodal artificial intelligence model launched by the company last year.
Read more »
OpenAI is phasing out GPT-4.5 for developersIan Carlos Campbell is a Contributing Reporter at Engadget, where he covers the big companies making screens for your pockets, and the weird ways they intersect with entertainment industry. Prior to Engadget, Ian was an Associate Editor at Inverse focused on AR, VR and mobile technology.
Read more »
OpenAI says its GPT-4o update could be ‘uncomfortable, unsettling, and cause distress’OpenAI rolled back a GPT-4o update for ChatGPT that caused the chatbot’s default personality to be “overly flattering or agreeable – often described as sycophantic” and that “sycophantic interactions can be uncomfortable, unsettling, and cause distress.
Read more »