[HN Gopher] Context Engineering Guide
___________________________________________________________________
Context Engineering Guide
Author : Bogdanp
Score : 49 points
Date : 2025-07-09 09:59 UTC (3 days ago)
(HTM) web link (nlp.elvissaravia.com)
(TXT) w3m dump (nlp.elvissaravia.com)
| Sebastian_09 wrote:
| Prompt engineering and now "context engineering" are really the
| poor man's engineering work when you're subject to model
| iterations and cannot control any of the stochasticity of the
| models... what we need is better science to understand how to
| control large model's output, not more LinkedIn AI influencers
| _Algernon_ wrote:
| Reads like an alchemist trying to write about how to create gold.
| behnamoh wrote:
| Great, yet another hyped up word to keep the AI hype going...
|
| I respect Karpathy, but I can't shake the feeling that recently
| has been doing more damage than good to the AI community. First
| he came up with "vibecoding" and now this one. What we need is
| better engineering approaches to build AI systems, not buzzy
| marketing words that only benefit AI companies.
| saturatedfat wrote:
| writing an essay on this if you'd be interested in reading a
| rough draft. i believe this very strongly and i think it's the
| UX that got us here and it's UX that'll take us out.
| 9dev wrote:
| Honestly, I don't think it's about AI even. The world has
| become so cynical, that's just how people make business now. If
| it wasn't context engineering, it'd be professional
| Watermelonism.
| evrimoztamur wrote:
| "Include relevant files directly, instead of letting the agent
| immediately grep your codebase, to save ninety seconds."
| apwell23 wrote:
| this is too convoluted and has no proof why it should be done
| this way
| gavinh wrote:
| This is exhausting.
| thorum wrote:
| The interesting part of context engineering (the actual
| engineering part) is figuring out how to gather the information
| the LLM needs to do a task correctly from your system. For
| example, the secret sauce of GitHub Copilot is how it decides
| what parts of your codebase to show the LLM. This is surprisingly
| hard when you need something other than simple RAG. In many cases
| the data source you need doesn't exist and you have to build it.
|
| The _prompt engineering_ side of the problem (how you structure
| your prompt) is trivial by comparison and will become less and
| less relevant as frontier models improve.
| jimby wrote:
| One thing I've noticed is llms are much better at outputting
| tabular data than json objects, especially for lists
| zmmmmm wrote:
| It seems endemic to software to me that people constantly want to
| brand things as "engineering" that aren't. They always want to
| call it engineering because it sounds better but they don't want
| to do nearly anything associated with engineering - rigorous
| process control, systematic documentation, specification of
| tolerances, resource usage etc etc.
|
| What's described here is mostly a list of barely disguised tips,
| tricks and heuristics. It's all fine until someone wants to put
| it in production and suddenly a "real" engineer has to take over
| and do the actual engineering.
|
| (and yes, I'm old - and grumpy!)
| bachmeier wrote:
| Anyone believing software engineering is a legitimate term
| should also accept context engineering as a legitimate term.
| Wikipedia's definition of engineering includes "The creative
| application of scientific principles to design or develop
| structures, machines, apparatus, or manufacturing processes, or
| works utilizing them singly or in combination" and context
| engineering as the term is used definitely qualifies if
| software engineering does.
___________________________________________________________________
(page generated 2025-07-12 23:00 UTC)