What Codex Actually Sends to the Model
I recorded the requests Codex generated for a 16-character prompt and measured what changed as it loaded instructions, exposed tools, read files, ran commands, received images, and compacted its history
0xkato
A blog about technology and stuff related
Latest posts
How to Research Technical Topics With AI
How I go from a technical question I cannot answer to an explanation I can reconstruct without the model
How LLMs Actually Work
A from-the-ground-up walkthrough of how modern LLMs work, from tokens to transformer blocks to the next-token loop
The Next Jump
Why I'm shifting from vulnerability research to machine learning security
CVE-2026-1678: DNS Parser Overflow in Zephyr
A walkthrough of CVE-2026-1678, a critical out-of-bounds write in Zephyr's DNS name parser caused by a stale bounds check
How CPU Caches Work
How CPU caches work, explained with a simple office analogy.
Is RCE Really Just Low Severity?
A friendly case study of a command injection in fmt::say, how it was fixed, and how impact and exposure shape severity
The Life of a Packet in the Linux kernel
A practical, plain-English tour of how Linux moves packets from write() to the wire and back
A Friendly Tour of Process Memory on Linux
A deep dive into how Linux manages process memory, page tables, and virtual address spaces
The Linux Boot Process: From Power Button to Kernel
A detailed walkthrough of the Linux boot process from power button to kernel initialization