Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
- abliteration
- llm
- transformer
- censorship-resistance
47,133 repositories indexed
1–5 of 5 · Most stars
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
ASCII transliterations of Unicode text - GitHub mirror
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.
Python application to setup and run streaming (contextual) bandit experiments.
A repo-native coding-agent loop harness for Claude, Codex, Copilot, and other CLI agents. Agents can edit. Gates decide what lands. You set the plan in motion. The agents take a prompt, and each iteration must update specs and commit through guardrails.