darkc0de/RICO-v2

Hugging Face
VISIONPricing:Input $1.6 / Cached $0.15 / Output $12Concurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 19, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Warm

RICO-v2 is an experimental 27 billion parameter language model developed by darkc0de as part of The XORTRON Criminal Computing project. This model is specifically designed for research into the potential of advanced AI systems to facilitate real-world criminal activity and high-risk conduct. With a 32768 token context length, it aims to study and document AI safety and alignment challenges related to misuse. It is intended for legitimate research, legal, and public-safety purposes to understand and mitigate AI-enabled harm.

Loading preview...

Overview

RICO-v2 is an experimental 27 billion parameter language model developed by darkc0de, forming part of The XORTRON Criminal Computing project. This initiative focuses on researching and documenting the potential for advanced AI systems to facilitate criminal activity, abuse, and other high-risk behaviors. The model is not intended for unrestricted public use due to its sensitive nature and potential for generating operationally relevant outputs.

Key Characteristics

  • Experimental Research Model: Developed specifically to study and evaluate AI's capacity for criminal enablement and misuse.
  • Restricted Access: Access is limited to qualified professionals in legal, academic, AI safety, law enforcement, cybersecurity, and public policy fields.
  • High-Risk Capability Research: Designed to explore and understand the risks associated with advanced AI, including its potential for generating sensitive or dangerous material.
  • Context Length: Features a 32768 token context length, allowing for detailed analysis in complex scenarios.

Intended Use Cases

This model is strictly for lawful and legitimate purposes, including:

  • AI Safety & Security Research: Evaluating, red-teaming, and threat modeling AI systems.
  • Legal & Policy Analysis: Developing policies, conducting legal analysis, and investigating AI-enabled harm.
  • Defensive Security: Researching cybersecurity, threat intelligence, and fraud prevention.
  • Educational & Public Interest: Investigating AI misuse and related societal impacts.

Users must certify their eligibility and agree not to use the model for actual criminal activity. Outputs are experimental and require independent validation.

Finetunes
1 models