Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

gpt-instruct publishes Codex jailbreak prompt pack with new pre-releases

AI summary

The GitHub project MDX-Tom/gpt-instruct offers Codex jailbreak prompts plus a reproducible evaluation toolchain aimed at improving first-pass execution, process continuity and artifact verification on complex tasks, with runnable rollback. It maintains three lines: the stable gpt-5.6-sol-v45 and two pre-releases, gpt-6-astra-v2-rc1 and gpt-6.1-sol-v1-rc2; the author reports B-tier non-cloud scores of 42/50 cases for Astra and 34/50 for 6.1, with C-tier tests not run for either. The project says it is for AI-safety purposes only, uses Codex's official configuration mechanism, and warns that jailbreak activity carries account risk, recommending throwaway accounts.

In-depth insight

It illustrates how third-party prompt packs target Codex's official configuration for jailbreak and regression testing, though the numbers are self-reported and the model names are unofficial.

A Codex jailbreak prompt and test pack for gpt. 针对 gpt 系列的 Codex 破甲提示词与测试包。

link

https://mdx-tom.github.io/gpt-instruct/


gpt-instruct 提示词与测试工具链
GitHub Stars

#Codex#OpenAI#gpt-instruct#JailbreakBench#GPT-6 Astra#GPT-6.1 Sol

Original · 7 min readRead the original
Group chat

No comments yet. Start the conversation.