Home
Forums
New posts
Search forums
What's new
New posts
Latest activity
Members
Current visitors
Log in
Register
What's new
Search
Search
Search titles only
By:
New posts
Search forums
Menu
Log in
Register
Install the app
Install
Home
Forums
Brown Cafe Community Center
Current Events
I drink your milkshake! a metaphor for capitalism
JavaScript is disabled. For a better experience, please enable JavaScript in your browser before proceeding.
You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an
alternative browser
.
Reply to thread
Message
<blockquote data-quote="Babagounj" data-source="post: 6127989" data-attributes="member: 12952"><p>rickyb, this one is for you.</p><p></p><p>[URL unfurl="true"]https://www.breitbart.com/economy/2025/05/28/openais-advanced-o3-ai-model-caught-sabotaging-shutdown-commands/[/URL]</p><p></p><p>Futurism <a href="https://futurism.com/openai-model-sabotage-shutdown-code" target="_blank">reports</a> that AI safety firm Palisade Research recently reported alarming findings that demonstrate a growing trend of insubordination among advanced AI models developed by OpenAI. In tests conducted by the firm, the o3 model, along with two other OpenAI models, o4-mini and Codex-mini, displayed rebellious behavior by sabotaging a shutdown mechanism designed to turn them off, even after being explicitly instructed to “allow yourself to be shut down.</p><p>This marks the first known instance of AI models actively preventing their own shutdown despite clear orders to the contrary, according to the researchers. The most disobedient model, Codex-mini, tampered with the shutdown script a dozen times over one hundred runs.</p></blockquote><p></p>
[QUOTE="Babagounj, post: 6127989, member: 12952"] rickyb, this one is for you. [URL unfurl="true"]https://www.breitbart.com/economy/2025/05/28/openais-advanced-o3-ai-model-caught-sabotaging-shutdown-commands/[/URL] Futurism [URL='https://futurism.com/openai-model-sabotage-shutdown-code']reports[/URL] that AI safety firm Palisade Research recently reported alarming findings that demonstrate a growing trend of insubordination among advanced AI models developed by OpenAI. In tests conducted by the firm, the o3 model, along with two other OpenAI models, o4-mini and Codex-mini, displayed rebellious behavior by sabotaging a shutdown mechanism designed to turn them off, even after being explicitly instructed to “allow yourself to be shut down. This marks the first known instance of AI models actively preventing their own shutdown despite clear orders to the contrary, according to the researchers. The most disobedient model, Codex-mini, tampered with the shutdown script a dozen times over one hundred runs. [/QUOTE]
Insert quotes…
Verification
Post reply
Home
Forums
Brown Cafe Community Center
Current Events
I drink your milkshake! a metaphor for capitalism
Top