# Posts by tag 'llm' — Liran Tal

AI security researcher, open-source maintainer, and author. Explore Liran Tal’s blog, research papers, developer tools, books, and conference talks.

Canonical: https://lirantal.com/tag/llm

*   Aug 2, 2026 · 17 min read

    ## [The Practical Second Brain: Building an LLM-Operated Markdown Knowledge Graph](/blog/practical-second-brain-llm-markdown-knowledge-graph)

    A hands-on guide to the files, schemas, workflows, governance, and maintenance routines behind an AI-assisted second brain.

    *   [ai](/tag/ai)
    *   [ai agents](/tag/ai-agents)
    *   [llm](/tag/llm)
    *   [knowledge management](/tag/knowledge-management)

     [![](/_astro/practical-second-brain-llm-markdown-knowledge-graph.CEcxBkpJ_Z19xT21.png)](/blog/practical-second-brain-llm-markdown-knowledge-graph)

*   Aug 1, 2026 · 16 min read

    ## [Building a Second Brain with LLMs and AI Agents](/blog/building-second-brain-llms-ai-agents)

    How a plain-Markdown knowledge graph becomes a durable context layer, operating system, and compounding productivity tool for AI-assisted work.

    *   [ai](/tag/ai)
    *   [ai agents](/tag/ai-agents)
    *   [llm](/tag/llm)
    *   [productivity](/tag/productivity)

     [![](/_astro/building-second-brain-llms-ai-agents.B3w2y6mA_2fR1l0.png)](/blog/building-second-brain-llms-ai-agents)

*   May 9, 2026 · 16 min read

    ## [Is Prompt Injection an Unsolvable Problem in AI?](/blog/is-prompt-injection-unsolvable-problem-ai)

    Prompt injection is not a bug you patch but an architectural limit baked into how LLMs process language. This post traces the problem from Gödel and Hofstadter to modern jailbreaks, agent skill supply chains, and why defenders must shift from elimination to survivability.

    *   [security](/tag/security)
    *   [ai](/tag/ai)
    *   [prompt injection](/tag/prompt-injection)
    *   [llm](/tag/llm)
    *   [ai agents](/tag/ai-agents)

     [![](/_astro/is-prompt-injection-unsolvable-problem-ai.CNHPYK7E_1xccHK.png)](/blog/is-prompt-injection-unsolvable-problem-ai)

*   Apr 20, 2026 · 12 min read

    ## [LLM Security Automation Isn’t a Drop-In Scanner Yet](/blog/llm-security-automation-isnt-a-drop-in-scanner-yet)

    An LLM Security Scanning and Review is a strong assist but a weeak gate. Why a \`/security-review\` slash command or agent harness is not a drop-in replacement for deterministic scanners yet: nondeterminism, confabulation, latency, cost, exploitability of generated code, and findings variance—grounded in how agent loops work and what BaxBench measures.

    *   [security](/tag/security)
    *   [llm](/tag/llm)
    *   [code review](/tag/code-review)
    *   [sast](/tag/sast)
    *   [machine learning](/tag/machine-learning)

     [![](/_astro/llm-secure-code-review-not-solved.GrIIxSzP_1sXo2o.png)](/blog/llm-security-automation-isnt-a-drop-in-scanner-yet)

*   May 15, 2025 · 5 min read

    ## [Gamifying the Future of Skill Development: From Open-Source Security to LLM Prompt Injection](/blog/gamifying-future-skill-development-open-source-security-llm-prompt-injection)

    Gamified learning is a great way to engage developers and teach them new skills. I share my experience building a game to teach developers about open-source security, playing Lakera's LLM prompt injection game and cheering for Israeli gamified learning startup Wilco.

    *   [gamification](/tag/gamification)
    *   [LLM](/tag/llm)
    *   [educational](/tag/educational)

     [![](/_astro/gamified-learning.Bag_tSd__Z2d5lNw.png)](/blog/gamifying-future-skill-development-open-source-security-llm-prompt-injection)

*   Feb 28, 2025 · 3 min read

    ## [What is an LLMs.txt File?](/blog/what-is-an-llms-txt-file)

    Building with Large Language Models (LLMs) requires context and metadata. The \`llms.txt\` file format is a simple text file that provides LLMs with relevant context and metadata.

    *   [LLM](/tag/llm)
    *   [ChatGPT](/tag/chatgpt)
    *   [AI](/tag/ai)

     [![](/_astro/what-is-llms-txt-file.m38k31jh_p7KKJ.jpg)](/blog/what-is-an-llms-txt-file)