20 Apr 2024

Researchers: when given 15 CVE descriptions, GPT-4 autonomously exploited 87% of the vulnerabilities, compared to 0% for every other model tested (Thomas Claburn/The Register)

Podcast cover

Techmeme

Open in Podwise to generate AI notes

Sign in to process this episode and unlock summaries, transcripts, highlights and translations.

Open in Podwise

Shownotes are not generated by Podwise.

Researchers: when given 15 CVE descriptions, GPT-4 autonomously exploited 87% of the vulnerabilities, compared to 0% for every other model tested (Thomas Claburn/The Register)