GitHub Trending / 2026-10-20

YuJunZhiXue/dsh-purge

DeepSeek Harness 破甲：让所有模型都能破甲，不同模型可换不同提示词；默认提示词面向国模「小码酱」。Jailbreak for every model — swap prompts per model. 求 Star 收藏 ⭐ 如要二开，请查看署名要求部分

Read original source

Source reference for YuJunZhiXue/dsh-purge. Screenshot not yet available. — Source record · preview pending · github.comOpen the source for the full page.

Source record

Source: GitHub Trending
Published: Not provided
First discovered: 2026-10-20 14:15:14.973Z
Last collected: 2026-10-20 14:15:14.973Z
Author: Not provided
Topic: AI infrastructure
Classification: Open-source projects & tools
Evidence level: E1 · source record; conclusions unverified

Recorded metrics

daily_stars · 1168 stars today
2026-10-20 14:15:14.973Z
GitHub daily Trending window; attention only

Research analysis

Rule-based research guidance derived from the source record. Audience and commercial demand require validation.

Project record

Repository: YuJunZhiXue/dsh-purge. Source account: DeepSeek Harness 破甲：让所有模型都能破甲，不同模型可换不同提示词；默认提示词面向国模「小码酱」。Jailbreak for every model — swap prompts per model. 求 Star 收藏 ⭐ 如要二开，请查看署名要求部分

Observed adoption & comparisons

Stars in source daily window: 1,168 stars today (Oct 20, 2026 UTC; GitHub daily Trending window; attention only) Recent records to compare: “Tencent Launches Hy4, One of the Leading Open-Source AI Models” (Hacker News, Nov 5, 2026); “Show HN: Resilient AI Worker Queue with Redis, BullMQ, and Budget Kill Switches” (Show HN, Nov 5, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.

Adoption decision

Evaluate it against the tool or manual workflow it would replace. The stored record supports discovery; it does not yet establish reliability, lower operating cost or commercial adoption.

Unverified requirements

Not verified: license permissions, required hardware, installation steps, maintenance status and a representative task with its failure cases.

Next test

Choose one real task and a current alternative. Record the commit, environment, input, output, elapsed time and failure behavior; retain the result before recommending adoption.