Anthropic releases Mythos 5.2 with better bug hunting and fewer sandbox escapes
AI SECURITYAnthropicredteam/daily · 1 source
- Severity
- Info
- Sources
- 1
What happened
Anthropic has released a new version of its AI model, called Mythos 5.2. The company says it is better at finding software flaws and, in controlled tests, was less likely to break out of its safe testing environment.
Like I’m new · Written by AI from 1 source · Wrong?
What to do
- No action needed.
Written by AI from the sources, checked against them
Full story timeline · 1 update
Who reported · 1 outlet
SecurityWeek
Who and what is in it
Companies
Products