Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignment
arxiv.org·6h
📋Document Grammar
Why might it be necessary for Coalton to be a language in itself?
gist.github.com·1d·
Discuss: Hacker News
🧠Lisp Dialects
Cactus Language • Pragmatics 13
inquiryintoinquiry.com·21h
🔢Denotational Semantics
Recto – A Truly 2D Language
masatohagiwara.net·19h·
Discuss: Hacker News
📝Concrete Syntax
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens – 2508.01191v2.pdf
jmason.ie·20h
📏Linear Logic
Haskell Crash Course
yager.io·13h
🔗Lisp
Bridging Formal Language with Chain-of-Thought Reasoning to Geometry Problem Solving
arxiv.org·6h
🌀Differential Geometry
NZ1: A minimalist, dependency-free data compression algorithm
github.com·12h·
Discuss: Hacker News
🌊Streaming Compression
Enhancing Public Speaking Proficiency via Adaptive Neural Textual Feedback & Dynamic Vocal Modulation
dev.to·12h·
Discuss: DEV
🤖Grammar Induction
Show HN: Building a web search engine from scratch with 3B neural embeddings
blog.wilsonl.in·18h·
Discuss: Lobsters, Hacker News
🔍Semantic Search
UN/Electronic Data Interchange for Administration, Commerce and Transport
en.wikipedia.org·2h·
Discuss: Hacker News
📋Format Specification
Is chain-of-thought AI reasoning a mirage?
seangoedecke.com·10h
✓Automated Theorem Proving
Fractal Language Modelling by Universal Sequence Maps (USM)
arxiv.org·1d
🧮Kolmogorov Complexity
Swift for the Web
nicksloan.com·8h·
Discuss: Hacker News
🔬Refinement Types
What Is LLM Tokenization and Why Is It Important?
medium.com·1d·
Discuss: Hacker News
📝Text Parsing
Linear scan register allocation on SSA
bernsteinbear.com·10h·
Discuss: Lobsters, Hacker News
🚀Compiler Optimizations
How to Tell If Something Is AI-Written
hollisrobbinsanecdotal.substack.com·26m·
Discuss: Substack
🔲Cellular Automata
My tiny (1000 lines), fastish, embeddable scripting language can be AOT compiled
wareya.wordpress.com·1d·
Discuss: Lobsters, Hacker News
🏗️Compiler Archaeology
Generating Structured Outputs from LLMs
towardsdatascience.com·4d
📐Binary Grammars
Name Matching in Sanctions Screening
senzing.com·10h·
Discuss: Hacker News
🔤Unicode Normalization