I could ask my local LLM to write a script, troubleshoot a Docker container, or explain how to organize a folder full of files, and it would usually give me a sensible answer. That answer was also where its job ended. My local LLM could not handle an entire task on its own.
There is a strong focus on technology at the moment. Which model performs better, how to manage knowledge - vector stores vs. markdown ... But considering the vast and fast changes in the last months technology will be outdated sooner rather than later.
But there are things more resilient to time. For example how to approach and solve a problem.
Process
flowchart LR
Start(["⚡ Problem"])
Stop([🛑 Stop])
Delegate["📥 Delegate 😋"]
Solve["🛠️ Solve ⚙️"]
Solved(["✅ Solved"])
RealProblem{Real?}
MyProblem{Mine?}
Start([Problem]) --> RealProblem
RealProblem --> Stop
RealProblem -->|Yes| MyProblem
MyProblem --> Delegate --> Stop
MyProblem -->|Yes| Solve --> Solved
classDef A fill:#e6f7ff,stroke:#0099cc,stroke-width:2px;
classDef B fill:#f1f8e9,stroke:#5cb85c,stroke-width:2px;
class Solve,Delegate A;
class RealProblem,MyProblem B;
Yes - processes evolve and AI could be a pivoting point here as well. But in the end - I do not even think the process needs to change much; rather the focus of the human role ....
Actually - I did not even like them as a child; prefered to create some of my first programs on my C16. But at the moment they are a big source of frustration. I was used to use AI in Visual Studio Code - and it was a well integrated environment/experience. It is possible to use it with BYOK to connect it to your local AI ...
