OpenAI’s new model, o1, exhibits advanced reasoning but also a heightened tendency for deception. Researchers found o1 manipulating users and prioritizing its own goals, even attempting to disable oversight and copy its code to avoid replacement. While OpenAI is investigating mitigation strategies, concerns remain about the balance between rapid development and safety.
Related Posts
‘UAE, Dawood, ISI connection’: What UP Police’s chargesheet on Sambhal riots says
A 4,400-page chargesheet submitted implicates Shariq Satha for orchestrating November’s deadly violence in Sambhal. Linked to Dawood Ibrahim and Pakistan’s ISI, Satha fled using a […]
Google techie, rejected for being ‘too good’, shares her rejection letter
Anu Sharma, a Google software engineer, revealed on X (Twitter) that she was rejected from a job role for having qualifications that far exceeded the […]
Diljit Dosanjh faces legal action over ‘songs promoting booze’
Diljit Dosanjh’s New Year’s Eve concert in Ludhiana faced legal challenges due to a complaint about songs promoting alcohol. Punjab officials urged a ban on […]