07-28-2023, 07:10 AM
AI researchers say they've found a way to jailbreak Bard and ChatGPT
<p style="float:right; margin:0 0 10px 15px; width:240px;"><img src="https://images.cointelegraph.com/cdn-cgi/image/format=auto,onerror=redirect,quality=90,width=840/https://s3.cointelegraph.com/uploads/2023-07/164bb4fa-2e76-4cce-83ec-bd1b319cc289.jpg"></p><p>Artificial intelligence researchers claim to have found an automated, easy way to construct adversarial attacks on large language models.</p>
https://cointelegraph.com/news/researche...atgpt-bard
<p style="float:right; margin:0 0 10px 15px; width:240px;"><img src="https://images.cointelegraph.com/cdn-cgi/image/format=auto,onerror=redirect,quality=90,width=840/https://s3.cointelegraph.com/uploads/2023-07/164bb4fa-2e76-4cce-83ec-bd1b319cc289.jpg"></p><p>Artificial intelligence researchers claim to have found an automated, easy way to construct adversarial attacks on large language models.</p>
https://cointelegraph.com/news/researche...atgpt-bard