←Back
Constitutional Classifiers: Defending against universal jailbreaks
www.anthropic.com617 posts0 readers
www.anthropic.com (from sitemap)
* Latest posts *
- [MAR.26.2026]project vend 1↗
- [MAR.24.2026]harness design long running apps↗
- [MAR.23.2026]science↗
- [MAR.20.2026]claude cowork↗
- [MAR.18.2026]eval awareness browsecomp↗
- [MAR.18.2026]demystifying evals for ai agents↗
- [MAR.16.2026]advanced tool use↗
- [MAR.11.2026]the anthropic institute↗
- [MAR.06.2026]coordinated vulnerability disclosure↗
- [MAR.06.2026]where stand department war↗
- [MAR.02.2026]enabling claude code to work more autonomously↗
- [FEB.28.2026]statement comments secretary war↗
- [FEB.25.2026]responsible scaling policy v3↗
- [FEB.20.2026]claude code security↗
- [FEB.05.2026]building c compiler↗
- [JAN.26.2026]claude code best practices↗
- [JAN.22.2026]AI resistant technical evaluations↗
- [JAN.21.2026]claude new constitution↗
- [JAN.15.2026]careers↗
- [JAN.07.2026]system cards↗