nbstme

Product-market fit has a prerequisite that most AI founders ignore. Before the market can pull your product, the model must be capable of doing the job. That's Model-Market Fit. When MMF Unlocks, Markets Explode (legal, coding...)

The best AI code is the code you delete. Models are eating abstractions faster than teams can adapt. Each model introduces a new paradigm shift. If you miss a paradigm shift, you’re dead.

After 30 years of clicking, scrolling, and optimizing pixels, websites are becoming obsolete. LLM agents will read and act for us, ending search engines, blue links, and traditional websites.

Exactly. Just a markdown file per user. Anthropic recommends that.

HAHAHA. Ok let's call it "transformation." As i wrote "The next decade of AI search will belong to systems that read and reason end-to-end. Retrieval isn’t dead—it’s just been demoted."

Thanks! Sorry if the flow was off

haha so true!

Why call it an ad? It’s not even on the company site. I only mentioned my company upfront so people get context (why we had to build a complex RAG pipeline, what kinds of documents we’re working with, and why the examples come from real production use cases).

But don’t you think LLM pricing is heading toward zero? It seems to halve every six months. And on privacy, you can hope model providers won’t train on your data, (but there’s no guarantee)

Why does grep in a loop fall apart? It’s expensive, sure, but LLM costs are trending toward zero. With Sonnet 4.5, we’ve seen models get better at parallelization and memory management (compacting conversations and highlighting findings).

LLMs > rerankers. Yes! I don't like rerankers. They are slow, the context window is small (4096 tokens), it's expensive... It's better when the LLM reads the whole file versus some top_chunks.

Appreciate the feedback. I’m not saying grep replaces RAG. The shift is that bigger context windows let LLMs just read whole files, so you don’t need the whole chunk/embed pipeline anymore. Grep is just a quick way to filter down candidates.

From there the model can handle 100–200 full docs and jot notes into a markdown file to stay within context. That’s a very different workflow than classic RAG.

Yes my point is that the entire RAG pipeline like ingest, chunk, embed, search with Elastic, rerank is in decline. Grep is far simpler. It’s trivial.

Exactly. AGI implies minimal tooling and very primitive tools.

hum because Claude Code pioneered the 'grep/glob/read' paradigm, so I felt the need to explain that what works well for coding files can also be applied to more complex documents.

100%. The speed of change is wild. With each new model, we end up deleting thousands of lines of code (old scaffolding we built to patch the models’ failures.)

Agree. It's a context/memory issue. Soon LLMs will have a 10M context window and they won't need to search. Most codebases are less than 10M tokens.

Why? What if LLMs could parallelize much of their reading and then summarize the findings into a markdown file, eliminating the need for complicated search?

The main use case I referenced is SEC filings search, which is quite different from code. Filings are much longer, less structured, and more complex, with tables and footnotes.

Haha! LLMs themselves are pure edge cases because they are non-deterministic. But if you add a 7-step pipeline on top of that, it's edge cases on top of edge cases.

It's mind blowing. It's so simple, elegant and... effective! Grep+glob and a lot of iterations is all we need.

Why Retrieval-Augmented Generation Won’t Survive the Context Revolution and the End of Chunking, Embeddings, and Rerankers as We Know Them.