Writing
Engineering post-mortems, not tutorials.
Hybrid search for Persian RAG: a field guide
Hybrid search for Persian (Farsi) RAG on PostgreSQL and pgvector: safe normalisation, RRF over dense and lexical ranks, no locale filter, bilingual tests.
RAG hallucination guardrails: a five-layer design
Five guardrails that stop a RAG assistant inventing answers: refusal before retrieval, a similarity floor, the prompt, a sentence gate and voice rules.
Choosing a pathology foundation model in 2026
No single pathology foundation model wins. What benchmarks, licences, task fit and compute say about UNI, CONCH and Virchow2. Research use, not diagnosis.
Streaming LLM guardrails: you can't unsay a token
Streaming LLM guardrails: a token can't be unsent. How NeMo, Guardrails AI and Bedrock trade speed for safety, and how a sentence gate checks each claim.
Legal AI hallucination cases pass 2,000: what to build
Court decisions on hallucinated AI content have passed 2,000. Why RAG alone did not fix it, and design patterns from my work on contract AI.
Persian token tax: what non-English LLM apps cost
Persian needed 1.53× the English tokens on GPT-4o's tokenizer and 3.26× on GPT-4's, across 1,012 parallel sentences. Method, results and what to test.
AI dubbing pipeline architecture: production lessons
How an AI dubbing pipeline works in production: four model stages, Persian pitfalls and the provider fallback that replaced silence after an outage.