Useful tool for cybersecurity researchers and red teamers.
This is a dev post classified by Jev as Security (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Useful tool for cybersecurity researchers and red teamers. Comparing how frontier models answer the same prompt or refusal check. - GODMODE CLASSIC : 5 model prompt pairings in parallel - refusal vs. completion on the same query - ULTRAPLINIAN : larger multi-model evaluation - Local-only : keep inference on your machine No signup. Keys stay in the browser. - http://github.com/elder-plinius/G0DM0D3
Posted by Md Ismail Šojal 🕷️ (56k followers) 1 h ago · 6 likes · 723 views · view the original post on X. Kept by the Dev Radar as Security. Tools mentioned: g0dm0d3.
More dev work like this
- Applications today can pull thousands of third-party packages, and AI agents are… — @depthfirstlabs
- 以前拿 Claude Code 做安全研究，很多时候还是得自己一步步引导。 — @bkdgiffug
- A malicious npm package was published with **completely valid provenance**. — @shehackspurple
- Grok @bot has a @1Password integration! You ask it to connect to your account, it… — @altryne
- Embedding a Gemini API key in client-side code can expose it to anyone using your app. — @freeCodeCamp
- With a $150K maximum reward, the stakes just got higher on CertiK Hunt. 🎯 — @CertiK
- Africans can build. what! — @Dominus_Kelvin
- 🚨[POC] CVE-2026-87902: WordPress Core versions up to and including 7.1.1 are affected… — @DarkWebInformer
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 23k posts from 5k X accounts over the last 21 days, 2.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-24 00:15 UTC. Full method.