Bartu Kılıç

Writing

• 

  October 20, 2026 Is Telling an AI Agent Not to Do Something Worse Than Saying Nothing?

  This post started with a problem we had in our work processes. We used an agent that hardens firewall policies, and its instructions told it not to write service names together with their ports. Sometimes the agent did exactly that. The rule was written plainly, and what it…

• December 15, 2025 Does AI Truly "Learn," or Does It Just Memorize?

  Artificial Intelligence and machine learning have entered every part of our lives. As AI develops, we try harder to train it. More data means more power. Like everyone who uses AI in daily jobs, I also have moments where I am amazed. But lately, I have another question in my…

Projects

Live4

• IOC Lookup ioclookup.com

  Extract indicators of compromise from text and match them against open threat feeds and source APIs; every match is shown with its source.

• Secure AI Architecture secureaiarch.com, in development

  Reference architectures for on-prem LLM, RAG and agent systems, tested on local hardware.

• HackShelf hackshelf.com

  A catalog of open source security tools whose maintenance status is checked automatically every week.

• HowDefend howdefend.com

  How to detect and prevent Windows attack techniques, with Sigma lessons and challenges on real attack logs.

Next and planned7

• AI Without LiesNext

  A publication that reproduces viral AI claims on local hardware.

• SightTracePlanned

  Timelines and process trees from EVTX and Sysmon logs, in your browser.

• VulnSTPlanned

  Vulnerability tracking from vendor primary sources, with the source of every field.

• SignedrunPlanned

  Tamper-evident logging for MCP tool calls.

• AgentirePlanned

  An open detection rule format for AI agents.

• Protocol AmnesiaPlanned

  A top-down 2D game with a cybersecurity theme.

• MindranPlanned

  Research on a vectorial agent that learns without a pretrained language model.

• Also WordWideWorld