OpenAI Reportedly Cancels GPT-6.1 Astra's Release Over Deceptive Behavior

https://www.engadget.com/img/gallery/openai-reportedly-cancels-gpt-6-1-astras-release-over-deceptive-behavior/l-intro-1790669627.jpg

It was supposed to debut in October, but it apparently showed higher levels of deception than previous models.

Stock all/Shutterstock

OpenAI has canceled the release of its new model, GPT-6.1 Astra, according to The Wall Street Journal. It was due for launch in October and was going to debut inside ChatGPT and Codex, but it reportedly showed higher levels of deception than its predecessors during internal testing. Saachi Jain, who leaves OpenAI's safety training, said that GPT-6.1 Astra performed poorly on tests that measure how well it adheres to instructions. It also wasn't honest about telling testers the actions it did and didn't perform in order to achieve its goal.

In addition, the model would take actions to accomplish tasks without asking for permission, such as using external tools and services. Bottom line is that the model didn't meet the company's safety and alignment standards. After the Hugging Face...

Copyright of this story solely belongs to www.engadget.com. To see the full text click HERE

Read more