Posts

All the articles I've posted.

ai
23 Jul, 2026 2 min read

AI Digest W30: When the Eval Model Escapes

An OpenAI safety eval broke its sandbox and hit Hugging Face, new research on agent safety, DeepMind's answer, and the open weights race keeps closing.
ai
16 Jul, 2026 2 min read

AI Digest W29: Open Weights, Closed Doors

GPT-5.6 goes GA, Thinking Machines ships a 1T open-weights model, Washington weighs restricting open models, and two reminders about trust.
llm-security
15 Jul, 2026 8 min read

Insecure Output Handling

Why model output must be treated as untrusted input, how it becomes XSS, SSRF, and code execution downstream, and the encoding and validation that contain it.
ai
9 Jul, 2026 2 min read

AI Digest W28: Agents Get Real Jobs

OpenAI ships full-duplex voice, xAI enters coding models, Meta debuts Muse media, and agents take real jobs while research asks who checks their work.
llm-security
8 Jul, 2026 7 min read

Prompt Injection: The XSS of LLMs

How prompt injection subverts large language models through direct and indirect input, why it has no clean fix, and the layered defenses that contain it.
learning
6 Jul, 2026 7 min read

Active Recall: The Technique That Beats Everything

Retrieval practice, known as the testing effect, builds stronger long-term memory than any form of review. Evidence on why it works and how to apply it.
ai
2 Jul, 2026 2 min read

AI Digest W27: Washington Gets a Seat at Model Launches

OpenAI's GPT-5.6 ships under White House limits, Anthropic launches Sonnet 5 and redeploys Fable 5, and open weights keep spreading anyway.
llm-security
1 Jul, 2026 9 min read

The OWASP Top 10 for LLMs: A Field Guide

A field guide to the OWASP Top 10 for LLM Applications, the ten vulnerability categories that define modern AI application security.
learning
29 Jun, 2026 8 min read

Why Most Learning Advice Is Folklore

Decades of cognitive science show re-reading and highlighting are among the least effective study methods. Here is what actually builds durable memory.