A friend of mine just pointed out that Grok “kids mode” has exactly the same settings as what companies demand for “enterprise mode” 😂
We have indeed infantilized businesses in modern society.
+1 for "context engineering" over "prompt engineering".
People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. When in every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window with just the right information for the next step. Science because doing this right involves task descriptions and explanations, few shot examples, RAG, related (possibly multimodal) data, tools, state and history, compacting... Too little or of the wrong form and the LLM doesn't have the right context for optimal performance. Too much or too irrelevant and the LLM costs might go up and performance might come down. Doing this well is highly non-trivial. And art because of the guiding intuition around LLM psychology of people spirits.
On top of context engineering itself, an LLM app has to:
- break up problems just right into control flows
- pack the context windows just right
- dispatch calls to LLMs of the right kind and capability
- handle generation-verification UIUX flows
- a lot more - guardrails, security, evals, parallelism, prefetching, ...
So context engineering is just one small piece of an emerging thick layer of non-trivial software that coordinates individual LLM calls (and a lot more) into full LLM apps. The term "ChatGPT wrapper" is tired and really, really wrong.
@govori_internet без да го познавам лично, когато чух какво казa Владо в подкаста все едно най-добър приятел ми го каза....стискам палци и за най-малкия шанс да се обърнат нещата❤️
Today, I'm celebrating my 11th landiversary! 🥳
In this last year, I’ve surpassed 30km, spotted another meteorite, entered a new quadrant, and encountered my toughest climb yet.
I've got more science-ing to do - so here's to more exploring on the Red Planet!