Skip to content
View kyahikaru's full-sized avatar
💭
Building
💭
Building
2 followers · 2 following

Block or report kyahikaru

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. cai-vs-rlhf-social-modulation cai-vs-rlhf-social-modulation Public

    Comparative evaluation of Constitutional AI vs RLHF guardrail robustness under sustained socially conditioned multi turn red teaming. Documents social modulation mechanism..

    1

  2. hinglish-prompt-injection-detector hinglish-prompt-injection-detector Public

    Lightweight hybrid defense against stealth prompt injection in Hinglish. Combines a 22‑rule Contextual Guard with an L12 SVM classifier. 98.4% detection on stealth benchmarks, 0.6% FPR, CPU‑only.

    Jupyter Notebook 1