Experimental browser for the Atmosphere
Cybersecurity researchers were able to bypass security features on ChatGPT by roleplaying with it. By getting the LLM to pretend it was a coding superhero, they got it to write password-stealing malware. #ML #AI #maleware #cybersecurity
Mar 23, 2025, 7:39 PM
{ "uri": "at://did:plc:zwzdlsvtvlxnpuacwhmqmd22/app.bsky.feed.post/3ll2ympbmo22d", "cid": "bafyreihkuov3hpwtcna5wujw4stbhxs7ytow5pugtno6aivmbxrt5b46vu", "value": { "text": "Cybersecurity researchers were able to bypass security features on ChatGPT by roleplaying with it. By getting the LLM to pretend it was a coding superhero, they got it to write password-stealing malware. #ML #AI #maleware #cybersecurity", "$type": "app.bsky.feed.post", "embed": { "$type": "app.bsky.embed.external", "external": { "uri": "https://www.aol.com/chatgpt-create-malware-strong-enough-113802509.html", "thumb": { "$type": "blob", "ref": { "$link": "bafkreiaygk7fccvuofwdztmmvvkrmblokhi4af2rphzfcasjtgizcoq3dm" }, "mimeType": "image/jpeg", "size": 388403 }, "title": "How do you get ChatGPT to create malware strong enough to breach Google's password manager? Just play pretend.", "description": "Cybersecurity researchers were able to bypass security features on ChatGPT by roleplaying with it, getting the bot to write password-stealing malware." } }, "langs": [ "en" ], "facets": [ { "index": { "byteEnd": 207, "byteStart": 204 }, "features": [ { "tag": "ML", "$type": "app.bsky.richtext.facet#tag" } ] }, { "index": { "byteEnd": 211, "byteStart": 208 }, "features": [ { "tag": "AI", "$type": "app.bsky.richtext.facet#tag" } ] }, { "index": { "byteEnd": 221, "byteStart": 212 }, "features": [ { "tag": "maleware", "$type": "app.bsky.richtext.facet#tag" } ] }, { "index": { "byteEnd": 236, "byteStart": 222 }, "features": [ { "tag": "cybersecurity", "$type": "app.bsky.richtext.facet#tag" } ] } ], "createdAt": "2025-03-23T19:39:28.528Z" } }