Anthropic confirms Mythos has already flagged more than 10,000 flaws
·2 min read
Compiled by KHAO Editorial
— aggregated from 1 source + 9 references discovered via search.
See llms.txt for citation guidance.
◌ Single Source
The company has published an update about Project Glasswing, a month after its launch.
Key facts
According to a recent report by the The Wall Street Journal, it's on track to post a revenue of $10.9 billion with an operating profit of $559 million for the quarter ending in June
Anthropic also used Mythos Preview to scan 1,000 open-source projects over the past few months and found 6,202 high- and critical-severity vulnerabilities out of 23,019
Cloudflare found 2,000 bugs, 400 of which are high or critical in severity
Anthropic has published an initial report for Project Glasswing, the cybersecurity initiative it launched in April that aims to prevent AI cyberattacks with, well, AI
Summary
Anthropic has published an initial report for Project Glasswing, the cybersecurity initiative it launched in April that aims to prevent AI cyberattacks with, well, AI. The company said that its partners' rate of bug-finding has increased by more than a factor of ten. Microsoft's recent announcement that its patch releases will "continue trending larger for some time" is apparently because of the bugs it found through Mythos Preview. The company explained in its report that it hasn't released Mythos Preview to the public yet, because no company (including itself) has developed safeguards strong enough to prevent models like it from being misused. For now, it's planning to work with partners like the US and other governments to expand the availability of Project Glasswing.