
heretic
Fully automatic censorship removal for language models
adversarial-attackai-securityeducation+3

Fully automatic censorship removal for language models

An interactive CLI application for interacting with authenticated Jupyter instances.

Artefacts for blog post on finding CVE-2025-37899 with o3

Explore and validate CVE-2026-42978 PoC with an integrated AI security tool, multi-protocol terminal, and autonomous agent suite for Windows Push…