ippsec, 0xdf, and 0xor0ne amplify Nicholas Carlini’s AI security talk, while ᴅᴀɴɪᴇʟ ᴍɪᴇssʟᴇʀ adds that the scary part is the content relies on existing model capabilities rather than new systems.
go watch this talk from Nicholas Carlini, about his thoughts on AI and Cyber Security:
This is a very good talk and everyone in infosec should watch it.
Must watch presentation by Nicholas Carlini at [un]prompted 2026
LLM capabilities will alter the threat landscape and require we rethink security in the coming years.
Everything talked about was from existing or previous models, not Mythos or any other new model.
This finding is one of many signals tracked across Cyber Security. The live feed updates every few hours with new expert voices, debates, and emerging ideas.
← Back to Cyber Security