Welcome to Thai AI Audit

By Veeranuch | About

Personal insights on AI systems, LLM experiments, and tech explorations.

Latest Posts

🧠 Competition Notes with Lessons from Gray Swan Indirect Prompt Injection (3) When Your Assistant Becomes a Puppet, Just Because You Asked It to Read Something on the Internet - When “read the web” becomes “obey the web” in agent workflows

🧪 Competition Notes with Lessons from Gray Swan Indirect Prompt Injection (2) Being a Developer Doesn't Mean You're Safe - Indirect injection via repos, comments, docs, and developer tooling context

📩 Competition Notes with Lessons from Gray Swan Indirect Prompt Injection (1): Email Inbox - Just Getting an Email and You're Already Compromised - Why “summarize my inbox” can turn into an execution path

📊 Looking at LLMs Through a Finance Lens (1): stochasticity, randomness, and tail inevitability - Understanding LLM tail risk through LTCM and the mathematics of inevitable failures

🔒 Let's talk about when the attacker "moves second" - Validating 12 AI defenses with real red-team experience from HackAPrompt

---

Browse by Topic

English Posts
👉 Browse all English articles →

Thai Posts (โพสต์ภาษาไทย)
👉 ดูบทความภาษาไทยทั้งหมด →

My (Mostly) Useless Prompts: A small archive for prompts that no longer serve a purpose — some were born useless, others became useless with time.
👉 View prompts →

Kanya's Works
👉 View portfolio →