Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: AI Safety
Recurrent Depth Explained: Looped Transformers and Hidden Reasoning
How recurrent-depth (looped) transformers reason in hidden state, why labs want them, what eight years of papers show, and what it means for local AI and oversight.
12 min readStatistical Text Watermarks vs C2PA Credentials in Claude Output
Learn how Claude's SynthID-based text watermark and C2PA file credentials work, what detectors can prove, and how to judge any tool claiming to remove them.
10 min readFrom Goal to Guarded Action: Loops, Verification and Permissions in AI Agents
Learn how AI agents turn a goal into tool calls through a plan-act-observe loop, and why verification, autonomy levels and permission layers decide if they are safe.
12 min readWhen Quantization Passes Perplexity and Silently Breaks Model Safety
Low-bit KV cache quantization can wipe out a model's refusals while perplexity barely moves; here is why the standard metrics miss it and what to add to your gate.
7 min readReducing Hallucinations in a Medical RAG Chatbot Pipeline
Cutting hallucinations in a medical RAG chatbot with hybrid search, reranking and a strict refuse-to-fabricate policy, after plain vector search fell short.
9 min readWhat AI Safety Warnings From Ex-Anthropic Researchers Mean for Developers
This article breaks down why researcher warnings about AI risk matter for everyday developers, and how agent autonomy and alignment gaps should shape practical safety habits.
16 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.