BitSharp / notes

Technical
notes.

Writing about the field, not about us. Every technical claim carries a clickable source with the date it was accessed; every note argues a thesis rather than surveying. A note without footnotes does not go on the site.

§ 01

A source, or silence.

The field moves faster than anyone’s memory, so nothing here is written from recall. Anything presented as current was checked on the day of writing — with a link and an access date on every entry.

§ 02

A thesis, not a survey.

A survey without an opinion is generated content. Every note defends a single sentence and says outright where certainty ends — a caveat written into the text is stronger than a smooth sentence with nothing behind it.

§ 03

What is not here.

Nothing about salaried work or projects covered by someone else’s IP. Nothing that cannot be checked through a link. No keyword-driven content — this is not a blog chasing traffic, it is an engineer’s registry of thinking.

Topic queue.

pool approved · ordered by thesis approval

Retrieval

  • modular RAG vs monolith
  • agentic RAG: when it pays off
  • GraphRAG: structure vs over-engineering
  • BM25 + vector hybrid, reranking
  • long context vs RAG

Agents

  • MCP as a tool standard
  • memory as architecture
  • context engineering
  • orchestration and the human entry point

Documents

  • OCR + LLM: the validation loop
  • enforcing response structure
  • when NOT to use an LLM

Production

  • evaluation: gold sets, LLM-as-judge
  • observability, A/B, rate limits
  • model routing and semantic cache
  • local vs API: GDPR
  • extreme quantization
001thesis
pending approval
Long context did not kill RAGPasting everything in costs you three times over: price, attention decay in the middle of the context, and time to first token.
002thesis
pending approval
In extraction, the LLM should read — not calculate, not decideSchema enforced at decoding, deterministic validation, a human approves only the exceptions.
003thesis
pending approval
Most „AI in the company” projects should be ordinary codeIf the rules can be written down, an LLM adds cost, latency and nondeterminism to a problem solved forty years ago.
Anatomy of an entry
0posts published3theses pending approval

How a note reads.

A different material from the model cards and results tables: serif in a single column, footnotes instead of threads, caveats in boxes, sources with access dates at the end. Three elements you will see in every entry:

footnote → source with a date

A technical claim ends in a reference[1], and every entry in the source list looks like this:

[1]  author/title · link· accessed: day of writing

thesis up front

Every entry opens with a thesis in an accented box — one sentence the text defends. As in a paper: the claim first, then the proof.

caveat in the open

Where certainty ends, the text says so openly — the dark box is part of the format, not fine print. The rule was tested on the 76.50% figure in the paper.