Kelly Mitchell
@kellmitchell.bsky.social
Tech PR @ Marketbridge (formerly fama PR)
Reposted by Kelly Mitchell
Outside experts pick up the slack on safety testing on OpenAI’s newest model release. Independent testing by SplxAI found GPT-4.1 was three times more likely than its predecessor to bypass security safeguards and allow intentional misuse. via @derekbjohnson.bsky.social cyberscoop.com/openai-gpt-4...
Outside experts pick up the slack on safety testing on OpenAI’s newest model release
OpenAI’s GPT-4.1 was released without a public safety report, prompting SplxAI researchers to test its resilience against misuse.
cyberscoop.com
April 23, 2025 at 4:22 PM
Outside experts pick up the slack on safety testing on OpenAI’s newest model release. Independent testing by SplxAI found GPT-4.1 was three times more likely than its predecessor to bypass security safeguards and allow intentional misuse. via @derekbjohnson.bsky.social cyberscoop.com/openai-gpt-4...
Reposted by Kelly Mitchell
OpenAI’s GPT-4.1 may be less aligned than the company’s previous AI models
OpenAI’s GPT-4.1 may be less aligned than the company’s previous AI models
In mid-April, OpenAI launched a powerful new AI model, GPT-4.1, that the company claimed “excelled” at following instructions. But the results of several independent tests suggest the model is less aligned — that is to say, less reliable — than previous OpenAI releases. When OpenAI launches a new model, it typically publishes a detailed technical […]
tcrn.ch
April 23, 2025 at 5:57 PM
OpenAI’s GPT-4.1 may be less aligned than the company’s previous AI models