GPT-5.5 matches heavily hyped Mythos Preview in new cybersecurity tests

Chronological Source Flow
Back

AI Fusion Summary

OpenAI’s GPT‑5.5, released publicly last week, matched Anthropic’s Mythos Preview in AI security tests, achieving a 71.4 % average on expert‑level Capture‑the‑Flag challenges. The AI Security Institute evaluated both models, noting similar cyber‑attack capabilities.
#OPENAI #ANTHROPIC #AISI #GPT-5.5 #MYTHOS_PREVIEW #CYBERSECURITY #AI
01/05 18:32 arstechnica.com
3 Πηγές

GPT-5.5 matches heavily hyped Mythos Preview in new cybersecurity tests

MYTHOSGPT-5.5ANTHROPICTESTCYBERSECURITYPOLITICS
01/05 20:56 decrypt.co

OpenAI's GPT-5.5 Matches Claude Mythos in Cyberattack Capabilities: AI Security Institute

ARTIFICIAL INTELLIGENCEPOLITICS
01/05 21:00 slashdot.org

GPT-5.5 Matches Heavily Hyped Mythos Preview In New Cybersecurity Tests

POLITICS
Comments
Loading...
0