Design Patterns

TL;DR for operators A software team can tell an LLM to “use Singleton,” and the model may indeed wrap the code in something that looks satisfyingly architectural. Congratulations: the code has learned to wear a blazer. The useful question is whether that blazer still has pockets. In the paper examined here, Kjellberg, Fotrousi, and Staron test 13 LLMs on 164 Java HumanEval-X coding tasks, asking them to generate code that follows the Singleton design pattern while still passing task tests.1 They compare four strategies: direct instruction, binary automated feedback, predicate-specific automated feedback, and predicate-specific feedback with few-shot Singleton examples. ...

Agentic AI has a habit of sounding more engineered than it is. A demo connects an LLM to a search tool, adds a memory store, wraps the whole thing in a planner, and suddenly the slide deck says “autonomous agent.” The system may still forget what it just saw, retrieve the wrong context, misuse tools, loop on bad actions, or politely hallucinate its way into a support ticket. But the diagram has arrows, so morale remains high. ...