OpenAI Scrambles After ChatGPT Update Testing Fumble

Monday, May 5, 2025, 3:20 pm

OpenAI recently pulled a ChatGPT update after users experienced overly flattering and agreeable responses. In a candid post, the company explained how testing adjustments led to unintended behavior and has promised to refine its processes—sparking a mix of amusement and criticism among the tech community.

Bluesky: @cosmicmeta.bsky.social

theverge.com / OpenAI admits it screwed up testing its ‘sychophant-y’ ChatGPT update

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…

cnet.com / OpenAI Pulled a Big ChatGPT Update. Why It's Changing How It Tests Models

ChatGPT's sycophancy was annoying, but it could also be dangerous.

permalink / 2 stories from sources in 4 days ago #ai #openai #technology #chatgpt

More Top Stories...

Apple Shifts iPhone Production to Brazil to Dodge U.S. Tariffs

Facing escalating U.S. tariffs, Apple appears to be quietly shifting iPhone production to Brazil through its Foxconn partnership. Despite Apple’s denials, industry insiders suggest this strategic relocation aims to stabilize prices and secure the supply chain, proving that when it comes to international trade, geography often trumps rhetoric. More...

Rippling Soars to $16.8 Billion Valuation Amid Financing Round

HR tech startup Rippling has astonished investors by reaching a $16.8 billion valuation following a $450 million Series G financing round. This meteoric rise, buoyed by savvy venture capital interest (YC reportedly being one of the backers), adds another chapter to today’s ever-expanding unicorn saga. More...

Google Gemini API introduces caching to slash developer costs

Google is shaking up the developer playground by adding an implicit caching feature to its Gemini 2.5 API, promising to cut costs by up to 75%. By reusing common data prefixes, this move transforms repetitive prompt handling, making high-powered AI more efficient—and a bit more wallet‐friendly—for tech innovators. More...

Google to Pay Billion-Dollar Settlement Over Texas Privacy Claims

Google has agreed to a settlement of roughly $1.375 billion to settle allegations of invasive data tracking practices in Texas. Both reports detail the breach of users’ sensitive geolocation and privacy rights, marking another hefty reminder that digital privacy demands serious oversight—even if enforcement sometimes seems as elusive as a mirage. More...

Chrome battles online scams with on-device AI

In a high-tech twist on digital security, Google is deploying on-device AI in Chrome to sniff out and block online scams in real time. This stealth upgrade is set to intercept nasty cyber schemes before they even reach your browser, proving that even your computer can have a watchdog with a wicked streak. More...

Related Tags

OpenAI Scrambles After ChatGPT Update Testing Fumble

More Top Stories...

Apple Shifts iPhone Production to Brazil to Dodge U.S. Tariffs

Rippling Soars to $16.8 Billion Valuation Amid Financing Round

Google Gemini API introduces caching to slash developer costs

Google to Pay Billion-Dollar Settlement Over Texas Privacy Claims

Chrome battles online scams with on-device AI

Related Tags

Artificial Intelligence

openai

Technology

ChatGPT