.learn() - page 5
what I have learned so far
-
Running a local LLM with llama.cpp: build, download, serve, benchmark
A minimal llama.cpp workflow for running GGUF models on your own machine — from the cmake build to an OpenAI-compatible server and llama-bench.
-
Pydantic with llm.with_structured_output — pitfalls and safeguards
Combining Pydantic models with LangChain's with_structured_output cleanly — avoiding prompt collisions, validation errors, and runaway evaluation loops.
-
Trimming constructor arguments with dependency injection: MVVM and the .NET Host
How DI simplifies object creation, and how the .NET Generic Host keeps the ever-growing constructors of MVVM view models short.
-
Dynamic Programming
How overlapping subproblems and optimal substructure turn recursive definitions into efficient algorithms.
-
Self-attention and the Transformer - cutting the sequential chain and referencing directly
Where an RNN passed context along by accumulating it through previous states, the Transformer looks up the tokens it needs directly. How self-attention removes the sequential structure, and how it connects back to attention Seq2Seq.