Semantic Compression

Caveman | Lithic Token Compression

A semantic constraint engine for Claude Code & Codex. Forces agentic communication into minimal-token lithic structures. Retain 100% technical accuracy while destroying up to 87% of output latency.

Dictionary Compression is finally here, and it's ridiculously good

Dictionary compression could completely change how applications send data over the web. It's recently gained broad support, and offers absurd real-world...

Quantization from the ground up | ngrok blog

A complete guide to what quantization is, how it works, and how it's used to compress large language models

Compression is prediction | ngrok blog

Compression and LLMs are trying to solve the exact same problem: predicting what comes next. Learn the fundamentals of compression and how better prediction leads to better shrinkage.

Aaron Steven White

computational semanticist. into modular synths and rum. https://aaronstevenwhite.io

Windsurf Codemaps: Understand Code, Before You Vibe It | Cognition

Codemaps is meant to offer a shared understanding of a system between humans and AI, enabling your AI to teach you about the code you are looking at quickly and elegantly. A codemap can be generated about any system or snippet to illuminate its code paths, helping users learn and recall. Codemaps allows AI to be a partner that explains code in an accurate and consistent way, rather than generating tons of inscrutable slop.

Predictive coding I: Introduction | Mark Sprevak

2024   Philosophy Compass, e12950

Better bitmap performance with Roaring bitmaps

Bitmap indexes are commonly used in databases and search engines. By exploiting bit-level parallelism, they can significantly accelerate queries. However, they can use much memory, and thus we might prefer compressed bitmap indexes. Following Oracle's lead, bitmaps are often compressed using run-length encoding (RLE). Building on prior work, we introduce the Roaring compressed bitmap format: it uses packed arrays for compression instead of RLE. We compare it to two high-performance RLE-based bitmap encoding techniques: WAH (Word Aligned Hybrid compression scheme) and Concise (Compressed `n' Composable Integer Set). On synthetic and real data, we find that Roaring bitmaps (1) often compress significantly better (e.g., 2 times) and (2) are faster than the compressed alternatives (up to 900 times faster for intersections). Our results challenge the view that RLE-based bitmap compression is best.

Lexicon Embeds Overview

There’s an excellent discussion and thread about syntax highlighting of code blocks happening today: I think most notably there’s some alignment around using a lexicon to represent code blocks (say Tangled’s strings) and embedding those, rather than just doing syntax highlighting w/in the constraints of a bsky post. This seems like a good place to hammer a bunch of things out.

Compression Dictionary Transport - HTTP | MDN

Compression Dictionary Transport is a way of using a shared compression dictionary to dramatically reduce the transport size of HTTP responses.

Aaron Steven White

computational semanticist. into modular synths and tiki. https://aaronstevenwhite.io

Structured CoT: Shorter Reasoning with a Grammar File

Constrain only the think block with a tiny grammar. On Qwen3.6 coding evals, explicit reasoning gets 22x-43x shorter without losing pass@1 in these runs.

Category Theory Illustrated - index

What does a debate between two ancient Greek philosophers have to do with the code running your computer? How can a simple map reveal the deepest secrets of the universe’s structure?