darkc0de/RICO

Hugging Face
VISIONPricing:Input $1.6 / Cached $0.15 / Output $12Concurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 7, 2026Architecture:Transformer0.0K Featherless Exclusive Warm

darkc0de/RICO is an experimental 27 billion parameter language model with a 32768 token context length, developed as part of The XORTRON Criminal Computing project. This model is specifically designed for research into AI's potential to facilitate criminal activity and other high-risk conduct. It is optimized for studying criminal enablement areas, with the original RICO model outperforming later versions for this specific use case.

Loading preview...

Model Overview

darkc0de/RICO is an experimental 27 billion parameter language model developed under The XORTRON Criminal Computing project. This model is specifically designed for research into AI safety and alignment, focusing on the potential for advanced AI systems to facilitate real-world criminal activity and high-risk conduct. The original RICO model has been noted to outperform its subsequent versions (v2, v3, v4) in key criminal enablement areas, making it particularly relevant for this specialized research.

Key Characteristics

  • Experimental Research Model: Intentionally developed to study and document AI's potential for malicious uses and abuses.
  • Specialized Focus: Optimized for exploring criminal enablement, abuse, and high-risk conduct scenarios.
  • Performance: The original RICO model demonstrates superior performance in its intended research area compared to later iterations.
  • Restricted Access: Not intended for unrestricted public use; access requires certification of legitimate professional, governmental, legal, academic, or AI-safety capacity.

Intended Use Cases

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

  • Research, evaluation, and benchmarking of AI's criminal enablement capabilities.
  • Red teaming, threat modeling, and policy development related to AI misuse.
  • Legal analysis, education, defensive security, and criminal-justice research.
  • Forensic analysis and investigation of AI-enabled harm.

Users are responsible for independently validating model outputs and ensuring compliance with all applicable laws and regulations, as the model may generate inaccurate, incomplete, or sensitive information. It is explicitly prohibited to use XORTRON or its outputs for committing or facilitating actual criminal activity.

Finetunes
3 models