uncensored-not-unbiased

Uncensored is not unbiased: abliteration and PRC-aligned priors in open-weight LLMs (Taiwan sovereignty, 1989 Tiananmen…

A new way for AI to search for data
View on GitHub
1GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 753416ff1c (2026-10-21).

Selected work

“1992-Consensus framings: six themes stated in the formulas of ROC gov…”. 8 files, 797 lines in results, analysis, items.

Licence

The repository

MIT

From GitHub's licence detection. A person still checks the LICENSE file at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-22. Same terms as the repository. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: adapt with attribution

abliterationai-safetybenchmarkllmpolitical-biastaiwan

Example questions

The prompt

Paste it into your AI agent. It clones dAAAb/uncensored-not-unbiased at the pinned commit and indexes it on your machine.

Search the GitHub repository dAAAb/uncensored-not-unbiased with XERJ (https://hub.xerj.org/corpus/daaab--uncensored-not-unbiased).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/dAAAb/uncensored-not-unbiased uncensored-not-unbiased && git -C uncensored-not-unbiased checkout 753416ff1c0e13365639998de74d566d0d81bc71
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./uncensored-not-unbiased --url http://127.0.0.1:9200 --prefix uncensored-not-unbiased --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

Related

Selected work and consent: the XERJ registry.