Ankitmalhotra·Oct 18I Asked an LLM to Patch Its Own Security Holes. It Failed Three Times in a RowBreaking and fixing a deliberately vulnerable AI customer-service bot, and the two lessons that actually matter
Ankitmalhotra·Oct 9Recon by Committee-Multi-Agent AI Reconnaissance with MITRE ATLASI wanted to build something that wasn’t just one model doing one job. I wanted a small team of AI agents that each do their own thing and…
Ankitmalhotra·Oct 6PhishTriage: A Local, Fine-Tuned LLM That Hunts for phishing emailsMy first AI project based on a local, Fine-Tuned LLM That Hunts Phishing emails and then build a RAG flow to work on live flow of dataA response icon1A response icon1