#ai-risk
#ai-risk
[ follow ]
#superintelligence #ai-alignment #openai #artificial-general-intelligence #anthropic #eliezer-yudkowsky
fromFuturism
1 week agoOpenAI Tries to Train AI Not to Deceive Users, Realizes It's Instead Teaching It How to Deceive Them While Covering Its Tracks
OpenAI researchers tried to train the company's AI to stop "scheming" - a term the company defines as meaning "when an AI behaves one way on the surface while hiding its true goals" - but their efforts backfired in an ominous way. In reality, the team found, they were unintentionally teaching the AI how to more effectively deceive humans by covering its tracks.
Artificial intelligence
fromBusiness Insider
3 weeks agoThe threat of 'superhuman' AI has sparked hunger strikes outside the offices of Anthropic and DeepMind
As AI advances, so too does the desperation of those trying to stop it. Two men, worried about the threat AI poses to humanity's future, are now on hunger strike outside the offices of Anthropic and DeepMind. For Guido Reichstadter, a 45-year-old activist, Sunday marked a week of protest without food. Reichstadter told Business Insider he plans to remain until the company responds to his concerns about the direction of AI development.
Artificial intelligence
Information security
fromComputerWeekly.com
1 month agoOkta makes AI identity play with Axiom acquisition | Computer Weekly
Okta is acquiring Axiom Security to integrate its PAM technology into Okta Privileged Access, strengthening privileged access controls for AI-related and other sensitive resources.
Podcast
fromPodcaster News
1 month agoBusiness Insider Co-Founder And Former CEO Henry Blodget Launches New Podcast In Partnership With Vox Media - Podcaster News
Solutions with Henry Blodget addresses pressing modern challenges with practical solutions, launching on August 18th under Vox Media's partnership.
fromChannelPro
2 months agoPressure mounts on MSPs as enterprises flock to managed cybersecurity services
“In light of the recent uptick of cyber incidents targeting MSPs, it is unsurprising that customers are scrutinizing MSPs more,” said Jamie Akhtar, CEO and Co-Founder of CyberSmart.
Information security
[ Load more ]