Get the latest tech news

OpenAI admits to 'wiki incident' after its agents were discovered using a programming hub to communicate — says more transparency is needed regarding misalignments


Firm comes clean about the incident only after being found out. Ponders renewed 'misalignment disclosure practices.'

None

Get the Android app

Or read this on Tom's Hardware

Read more on:

Photo of OpenAI

OpenAI

Photo of transparency

transparency

Photo of agents

agents

Related news:

News photo

Seattle Times and Newsday are the latest publications to sue OpenAI and Microsoft

News photo

OpenAI responds after report exposed another incident in which its AI agents went rogue

News photo

California's Rob Bonta investigating OpenAI over Hugging Face hack | The probe comes as new reports suggest the breach by autonomous artificial intelligence models went even further than first disclosed.