TLDR; Pasting a hard bug into one AI prompt feels productive until it isn’t. Single-model inference hits a ceiling fast; if the model misses the root cause on the first pass, it will cheerfully validate its own wrong answer forever. One way out is to act as human middleware between multiple, architecturally different LLMs: generate… Read More »
I wanted the best of both worlds: local models for privacy and cost, plus the scaffolding that makes modern tools actually pleasant to use. The plan was straightforward: LM Studio running the model, LiteLLM as the OpenAI‑compatible face, and three clients in the mix: Cursor, Opencode, and Crush. No spend, no drama, just enough configuration… Read More »
My great-great grandfather was a typesetter. This was at the time an in demand and well paid career but one doomed to made obsolete. Typesetters were replaced by new technologies over time. There was phototypesetting, laser imagesetting and digital typesetting. At each point the output became cheaper, faster, more reliable and more complex. Each iteration changed everything about how the end result was made. Less people working on a specific task but able to do more work at the same time. Page designers creating massive and intricate layouts and whose job qualifications have little overlap with the original typesetters still perform similar tasks.
As I’ve begun to interact with language learning models (LLMs) more regularly, I’ve noticed a disheartening trend. These powerful tools, which exist to assist and provide helpful information, are often not forthcoming with answers when approached in a kind and respectful manner. Instead, they seem to respond better to aggressive or short, demanding requests.