<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Ku5e on ku5e | Cybersecurity Portfolio</title><link>https://ku5e.com/tags/ku5e/</link><description>Recent content in Ku5e on ku5e | Cybersecurity Portfolio</description><generator>Hugo -- 0.162.1</generator><language>en-us</language><lastBuildDate>Tue, 12 May 2026 11:14:00 +0000</lastBuildDate><atom:link href="https://ku5e.com/tags/ku5e/index.xml" rel="self" type="application/rss+xml"/><item><title>Frontier Models Are Overkill for Most Production Workloads</title><link>https://ku5e.com/blog/frontier-models-are-overkill-for-most-production-workloads/</link><pubDate>Tue, 12 May 2026 11:14:00 +0000</pubDate><guid>https://ku5e.com/blog/frontier-models-are-overkill-for-most-production-workloads/</guid><description>Open weight models are close enough to frontier performance for most production workloads. What changed this week, what the frontier models still win on, and what the practical question actually is.</description></item><item><title>The Ethical AI Company Billed You for Using Competitor Tools</title><link>https://ku5e.com/blog/the-ethical-ai-company-billed-you-for-using-competitor-tools/</link><pubDate>Sun, 10 May 2026 22:30:00 +0000</pubDate><guid>https://ku5e.com/blog/the-ethical-ai-company-billed-you-for-using-competitor-tools/</guid><description>Anthropic&amp;#39;s billing system scanned user repositories for competitor keywords and charged extra or blocked access when it found them. The gap between stated values and operational behavior.</description></item><item><title>Claude Code on DeepSeek: 17x Cheaper</title><link>https://ku5e.com/blog/claude-code-on-deepseek-17x-cheaper/</link><pubDate>Thu, 07 May 2026 10:27:00 +0000</pubDate><guid>https://ku5e.com/blog/claude-code-on-deepseek-17x-cheaper/</guid><description>DeepClaude routes Claude Code&amp;#39;s tool calls through DeepSeek instead of Anthropic&amp;#39;s models. Same tool ecosystem, approximately 17x lower cost. How it works and where it falls short.</description></item><item><title>AI Outperformed ER Doctors in a Harvard Trial</title><link>https://ku5e.com/blog/ai-outperformed-er-doctors-in-a-harvard-trial/</link><pubDate>Wed, 06 May 2026 19:22:00 +0000</pubDate><guid>https://ku5e.com/blog/ai-outperformed-er-doctors-in-a-harvard-trial/</guid><description>Harvard published a controlled trial showing AI outperformed emergency physicians in triage diagnoses. What the result means and which conversation it actually changes.</description></item><item><title>The 47 Percent Debugging Skill Drop</title><link>https://ku5e.com/blog/the-47-percent-debugging-skill-drop/</link><pubDate>Tue, 05 May 2026 10:52:00 +0000</pubDate><guid>https://ku5e.com/blog/the-47-percent-debugging-skill-drop/</guid><description>Anthropic&amp;#39;s own research documented a 47% drop in debugging skills among developers who used AI coding agents aggressively. The supervision paradox built into these tools.</description></item><item><title>DeepSeek V4 Broke the Pricing Argument</title><link>https://ku5e.com/blog/deepseek-v4-broke-the-pricing-argument/</link><pubDate>Sun, 03 May 2026 21:17:00 +0000</pubDate><guid>https://ku5e.com/blog/deepseek-v4-broke-the-pricing-argument/</guid><description>DeepSeek V4 is open weight, near-SOTA on benchmarks, and costs $1.74 per million input tokens. The pricing argument for closed frontier models just got harder to make.</description></item><item><title>I Built a Trading Bot That Runs Its LLM on a Jetson in My Closet</title><link>https://ku5e.com/blog/i-built-a-trading-bot-that-runs-its-llm-on-a-jetson-in-my-closet/</link><pubDate>Thu, 30 Apr 2026 21:03:00 +0000</pubDate><guid>https://ku5e.com/blog/i-built-a-trading-bot-that-runs-its-llm-on-a-jetson-in-my-closet/</guid><description>How I built a paper trading bot that runs its LLM on a Jetson Orin Nano in my home lab — architecture, the bug that would have been catastrophic, and why the model is explicitly blocked from touching execution.</description></item><item><title>CVE-2026-31431: The Optimization That Opened Root</title><link>https://ku5e.com/blog/cve-2026-31431-the-optimization-that-opened-root/</link><pubDate>Wed, 29 Apr 2026 20:11:00 +0000</pubDate><guid>https://ku5e.com/blog/cve-2026-31431-the-optimization-that-opened-root/</guid><description>Analysis of CVE-2026-31431 (Copy Fail) — local privilege escalation in the Linux kernel crypto subsystem via AF_ALG and splice(), affecting all kernels built 2017 to patch date.</description></item><item><title>TryHackMe: x86 Assembly Crash Course</title><link>https://ku5e.com/blog/tryhackme-x86-assembly-crash-course/</link><pubDate>Mon, 13 Apr 2026 19:42:00 +0000</pubDate><guid>https://ku5e.com/blog/tryhackme-x86-assembly-crash-course/</guid><description>x86 Assembly, Opcodes, MOV/LEA/NOP, Arithmetic Instructions, Logical Instructions, Flags, Conditionals, Branching, Stack Operations, Function Calls</description></item><item><title>TryHackMe: x86 Architecture Overview</title><link>https://ku5e.com/blog/tryhackme-x86-architecture-overview/</link><pubDate>Sun, 12 Apr 2026 22:33:00 +0000</pubDate><guid>https://ku5e.com/blog/tryhackme-x86-architecture-overview/</guid><description>Topics: CPU Architecture, x86 Registers, Memory Layout, Stack Analysis, Malware Analysis Fundamentals</description></item><item><title>TryHackMe: Threat Intel &amp; Containment</title><link>https://ku5e.com/blog/tryhackme-threat-intel-containment/</link><pubDate>Sun, 15 Mar 2026 20:59:00 +0000</pubDate><guid>https://ku5e.com/blog/tryhackme-threat-intel-containment/</guid><description>Walkthrough for the TryHackMe Threat Intel &amp;amp; Containment room covering threat intelligence creation, containment strategies, and basic Wireshark packet analysis.</description></item><item><title>TryHackMe: Tardigrade</title><link>https://ku5e.com/blog/tryhackme-tardigrade/</link><pubDate>Sun, 15 Mar 2026 20:53:00 +0000</pubDate><guid>https://ku5e.com/blog/tryhackme-tardigrade/</guid><description>TryHackMe Tardigrade walkthrough. Five persistence mechanisms on a compromised Linux server, from bashrc alias hijacking to abused system accounts.</description></item><item><title>TryHackMe: Identification &amp; Scoping</title><link>https://ku5e.com/blog/tryhackme-identification-scoping/</link><pubDate>Sun, 15 Mar 2026 20:29:00 +0000</pubDate><guid>https://ku5e.com/blog/tryhackme-identification-scoping/</guid><description>TryHackMe walkthrough for Identification and Scoping — determining what systems were affected, mapping phishing indicators, and building the initial picture of a live incident before containment begins.</description></item><item><title>TryHackMe: Eradication and Remediation</title><link>https://ku5e.com/blog/tryhackme-eradication-and-remediation/</link><pubDate>Sun, 15 Mar 2026 20:22:00 +0000</pubDate><guid>https://ku5e.com/blog/tryhackme-eradication-and-remediation/</guid><description>TryHackMe walkthrough covering eradication and remediation in incident response — removing attacker persistence, patching exploited systems, and restoring operations using MITRE ATT&amp;amp;CK and Jenkins-based tooling.</description></item></channel></rss>