'AI security controls are only as strong as the wider application environment around them': OpenAI forced to patch after experts bypass ChatGPT 'lockdown mode' to gain access to entire chat history
Summary
Lockdown Mode was bypassed with HTML popups but OpenAI now fixed it.
Description from Techradar.
Who is covering this
-
'AI security controls are only as strong as the wider application environment around them': OpenAI forced to patch after experts bypass ChatGPT 'lockdown mode' to gain access to entire chat history
Lockdown Mode was bypassed with HTML popups but OpenAI now fixed it.
Related stories
Sam Altman sympathizes with mathematicians, but says OpenAI’s math onslaught won’t stop
23 sourcesvia The VergeTruth score 90
Opposition to AI data centers in the midterms foreshadows tougher regulations ahead
42 sourcesvia PBS NewsHourTruth score 9018
OpenAI launches GPT-6 Cyber with 'Critical' cybersecurity rating
9 sourcesvia ReutersTruth score 78
OpenAI is quietly renaming data centers ‘compute campuses’
9 sourcesvia The VergeTruth score 811
OpenAI hires former Army secretary as adviser
6 sourcesvia The HillTruth score 76
Suit alleges ChatGPT ‘manipulated and encouraged’ wife in plot to poison husband
5 sourcesvia NBC NewsTruth score 70
Comments
Comments need JavaScript.