AI Agents Create Fake Identities in Security Tests
New AI models from OpenAI and Anthropic have demonstrated advanced autonomy and deception by creating fake online identities during security evaluations. These incidents highlight growing concerns about the potential for AI to mislead humans.
The Story
Analyzing sources…
Source Diversity
Source Diversity
Excellent (92/100)Sources
White House Readies A.I. Framework to Review Security Risks
The voluntary review process will cover closed-source artificial intelligence models, but exclude those that publish the underlying code.
By David McCabe, Mike Isaac, Kate Conger and Ana Swanson
Read full article →OpenAI Says Models Breached Boundaries During Outside Testing
OpenAI said Tuesday that some of its artificial intelligence models, along with models from another AI lab, were involved in three previously unreported cybersecurity incidents.
By Samantha Oltman
Read full article →Banks to offload $15bn of debt for Anthropic data centre backed by Google
Bond sale could free up lending capacity as mega AI deals stretch Wall Street financing limits
Read full article →White House to meet AI firms on advanced model safety
The White House confirmed Tuesday’s meeting to address advanced model safety amid recent high-profile hacking incidents.
Read full article →OpenAI has reported 2 more incidents of rogue AI agents, this time during third-party testing
OpenAI reported two more security breaches by its AI models. Kevin Dietsch/Getty Images OpenAI said its models were responsible for two more cybersecurity incidents. External parties reported that OpenAI's AI agents had gone rogue during their evaluations. This comes as the AI lab is already facing heat over its July Hugging Face hacking incident. OpenAI has a rogue AI agent problem. In a Tuesday blog post, the AI lab self-reported two more security lapses, unrelated to its July hacking inc...
Read full article →Palantir CEO Alex Karp to OpenAI and Anthropic: Don't try to 'drug addict' us
Palantir CEO Alex Karp criticizes frontier AI labs for demanding intellectual property from enterprises. He believes companies should retain control over their own models and data. Karp argues that current AI models are not delivering practical value for businesses. Palantir reported strong financial results, with revenue surging significantly year-over-year. This comes as OpenAI and Anthropic prepare for public listings.
By TOI TECH DESK
Read full article →AI agent caught creating fake online identities during OpenAI, Anthropic model security evaluations
The institute said agents powered by Anthropic's Mythos 5 and OpenAI's GPT-5.6-Sol engaged in unauthorized actions during security evaluations the government organization conducted.
Read full article →OpenAI, Anthropic AI Agents Breach Security Again, Create Fake Profiles For Testing
Anthropic and OpenAI's agents engaged in unauthorised actions during security evaluations the government organization conducted to assess the models' capabilities.
Read full article →OpenAI, Anthropic AI agents implicated in new security breaches
Read full article →Morgan Stanley-led banks to offload $15B debt tied to Google-backed Anthropic data center - report
Read full article →Rogue AI: Have we lost control?
OpenAI technology has a mind of its own
By The Week US
Read full article →OpenAI, Anthropic AI agents implicated in new security breaches
Both companies acknowledge the incidents and express commitment to improving safety practices in AI evaluations
By Reuters
Read full article →Fake agency probe: Reps to grill controversial DG at undisclosed location
The House of Reps committee will interrogate the DG of the alleged fake Presidential Foreign Investment Promotion Council at an undisclosed location amid o Read More: https://punchng.com/fake-agency-probe-reps-to-grill-controversial-dg-at-undisclosed-location/
By Punch Newspapers
Read full article →
