ai
Anthropic Releases Version of Mythos Restricted on Cybersecurity Tasks
Anthropic is releasing a version of Mythos that prevents the model from performing cybersecurity operations. The restriction applies across the widely available release.
techjuice.pkAudio version
Tap play to generate a narrated version.
Developing·Limited corroboration so far. This page will refresh as more sources emerge.
Anthropic is releasing a version of Mythos that will be blocked from carrying out cybersecurity tasks. The company stated the restriction applies to the version made available to the public.
No further technical specifications or rollout timeline were provided in the announcement. The measure limits model functions related to cybersecurity without affecting other capabilities.
Transparency
2 sources · across multiple outlets
CorroborationLimited · 2 sources
