Skip to content

Navigation Menu

Sign in
Sign up
@NarchTech
NarchTech
Follow
  • Joined Aug 19, 2026

Block or report NarchTech

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.

Content in all repositories owned by your account will be closed.
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

Popular repositories Loading

  1. narchat narchat Public

    An end-to-end encrypted messenger built to be understood, not just trusted. Pilot + paper.

    JavaScript

  2. turkish-i-breaks-software turkish-i-breaks-software Public

    The Turkish I still breaks software (and AI agents): article (EN+TR), citations, and a reference implementation of locale-correct Turkish case folding.

    HTML

  3. written-not-wired written-not-wired Public

    Written ≠ Wired: Hunting Fake-Green in Agent Systems — preprint + PDF (CC BY 4.0)

    HTML

  4. memory-poisoning-referee-report memory-poisoning-referee-report Public

    Verification referee report on arXiv:2606.04329 (memory poisoning) — resolving a 70–95% vs 50.46%/41.05% conflicting-claims discrepancy by primary-source grep verification.

    HTML

  5. agent-identity-portability agent-identity-portability Public

    Flagship study: can a disk-anchored agent identity be operated across foundation-model families? A blind, internally pre-sealed A/B comparison (D1-D4).

    HTML

  6. defensible-by-construction defensible-by-construction Public

    Defensible by Construction: Five Practices for Trustworthy AI-Agent Deliverables (preprint, EN+TR)

    HTML

AltStyle によって変換されたページ (->オリジナル) /