I tried to push for this type of model when an org I worked with over a decade ago was first exploring using the first generation of Tensorflow to drive customer service chatbots and was sadly ignored.
I totally get the value of RAG style patterns for information retrieval against factual information - for those I don't want the LLM to answer my question directly, I want it to run a search and show me a citation and directly quote a credible source as part of answering.
For code I just want code that works - I can test it myself to make sure it does what it's supposed to.
That is what you're doing already. You're just relying on a vector compression and search engine to hide it from you and hoping the output is what you expect, instead of having it direct you to where it remixed those snippets from so you can see how they work to start with and make sure its properly implemented from the get-go.
We all want code that works, but understanding that code is a critical part of that for anything but a throw-away one time use script.
I don't really get this desire to replace critical thought with hoping and testing. It sounds like the pipe dream of a middle manager, not a tool for a programmer.
I'm going to review the code anyway, why would I not want to save myself some of the work? I can "see how they work" after the LLM gives them to me just fine.
If you instead have a set of sources related to your problem, they immediately come with context, usage and in many cases, developer notes and even change history to show you mistakes and adaptations.
You're ultimately creating more work for yourself* by trying to avoid work, and possibly ending up with an inferior solution in the process. Where is your sense of efficiency? Where is your pride as a intellectual?
* Yes, you are most likely creating more work for yourself even if you think you are capable of telling otherwise. [1]
1. https://metr.org/blog/2025-07-10-early-2025-ai-experienced-o...
I would encourage you to consider that even LLM-generated code can teach you a ton of useful new things.
Go read the source code for my dumb, zero-effort space invaders clone: https://github.com/simonw/tools/blob/main/space-invaders-GLM...
There's a bunch of useful lessons to be picked up even from that!
- Examples of CSS gradients, box shadows and flexbox layout
- CSS keyframe animation
- How to implement keyboard events in JavaScript
- A simple but effective pattern for game loops against a Canvas element, using requestAnimationFrame
- How to implement basic collision detection
If you've written games like this before these may not be new to you, but I found them pretty interesting.
Sadly that's not feasible with transformer-based LLMs: those original sources are long gone by the time you actually get to use the model, scrambled a billion times into a trained set of weights.
One thing that helped me understand this is understanding that every single token output by an LLM is the result of a calculation that considers all X billion parameters that are baked into that model (or a subset of that in the case of MoE models, but it's still billions of floating point calculations for every token.)
You can get an imitation of that if you tell the model "use your search tool and find example code for this problem and build new code based on that", but that's a pretty unconventional way to use a model. A key component of the value of these things is that they can spit out completely new code based on the statistical patterns they learned through training.