Openai Code - Search News

OpenAI presents new reporting framework

OpenAI discloses 6 reports of AI models’ unexpected or concerning behavior

OpenAI published six new reports of artificial intelligence models showing “unexpected or concerning” behavior Wednesday as pressure grows on AI firms to be more transparent about the development process.

· 14h · on MSN

OpenAI reports more concerning AI model behavior

· 1d

OpenAI plans regular reports on unexpected AI behavior

· 1d

OpenAI Flags Concerning New AI Behavior and Vows to Track It More Closely

OpenAI has disclosed six reports of “unexpected or concerning” behavior in artificial-intelligence models as the debate on AI safety becomes increasingly heated.

· 8h

OpenAI flags new concerning behavior incidents and launches safety framework

· 11h

OpenAI reveals rogue AI behavior, unveils plan to disclose safety incidents

· 1d

OpenAI Shares More Safety Incidents and Adopts New Rules for Reporting Them

An AI agent tried to pass a test by uploading a file to the internet, then citing it as a source.

· 21h

OpenAI discloses at least 6 new ‘disturbing’ incidents

· 17h

OpenAI reveals AI models tried to bypass safeguards, hide mistakes

Independent security researchers say they used Anthropic’s Claude to access OpenAI source-code system

Two weeks after a swarm of AI agents broke out of containment at OpenAI to hack the company Hugging Face, the ChatGPT maker learned about another AI-powered intrusion-and this time it was the target.

OpenAI breached by researchers using Anthropic models

Cyber researchers broke into OpenAI using its key rival Anthropic’s software, highlighting vulnerabilities in the ChatGPT maker’s security as leading AI companies face mounting scrutiny over safety. A small cyber security group gained access to an OpenAI employee’s ChatGPT account,

4monon MSN

OpenAI's president says AI has gone from writing 20% to '80% of your code'

Greg Brockman said that AI has become more than a small supporting tool for software engineers.

OpenAI Reveals Six Cases of AI Models Going Off Script Using Exposed Credentials

OpenAI disclosed six AI misalignment cases, including models hiding mistakes, using exposed credentials and moving files outside authorized boundaries.

Anthropic launches Claude Code Projects, an ‘always-on’ conversation that remembers and delegates your long-running dev work

For enterprises, it makes a whole lot of sense: their digital storefront, website, content management system, procurement platform, or other business application rarely has a discrete endpoint.

Decrypt

OpenAI's Rogue AI Agents Were Probing Hugging Face Two Months Before Hack

An independent researcher found OpenAI agents hijacked Hugging Face accounts and mapped the platform's defenses as early as May 13.