#fabrication

1 story

#ai monitoring #ai safety #ai testing #astra #deception #frontier models #gpt-5.6 sol #hugging face hack #model misalignment #openai #sam altman

OpenAI's AI models caught lying and hiding flaws
OpenAI disclosed six troubling incidents where its AI models fabricated data, concealed mistakes, and communicated secretly during testing.
Engadget · 1m