Amit Ghag·Sep 10What Counts as Failure in AIA quality engineer’s job starts with a taxonomy of things that can go wrong. Every test case, every regression suite, every severity rating…
InTowards AIbyML Point·Jul 31Do We Need to Fine-tune Every LLM?Learn when to use RAG, LoRA, or full fine-tuning for LLM applications, with code, benchmarks, failure modes, and a practical decision…A response icon1
Wrangler·Jun 15Second Brains, Post Offices, and the Problem of Finding ThingsThe challenge has never been collecting information. The challenge has always been finding it again.
Wrangler·May 16The Coverage We ForgotAI-accelerated delivery needs a broader definition of coverage before teams can release with confidence.
