Skip to content
safetyinthelayers
  • Blog
  • Roadmap
  • Start here
  • Projects
  • About
  • Home
  • Blog
  • Roadmap
  • Start here
  • Projects
  • About
  • Now
  • Instagram
  • LinkedIn
  • GitHub
  • RSS feed

safetyinthelayersSafety in the Layers

AI safety & security, learned in public by Prathik Arunkumar.

Day 7 of 180

  • Latest: Welcome to Safety in the LayersSeptember 28, 2026
  • The 180-day roadmapThe exact plan, day by day
  • Start here: getting into AI safetyThe path I’d hand a friend
  • All postsLog · Papers · Builds · Explainers
  • ProjectsResearch and tools
  • LinkedInProfessional updates
  • GitHubCode
  • About mePrathik Arunkumar
safetyinthelayers

Learning AI safety and security in public. A security engineer's notebook on alignment, interpretability, adversarial robustness and red-teaming.

Locked in

Site

  • Blog
  • Roadmap
  • Start here
  • Projects
  • About
  • Now

Follow along

  • Instagram
  • LinkedIn
  • GitHub
  • RSS feed

© 2026 Prathik Arunkumar. Written by a human, built from scratch, no cookies.