AI Illustration for Educators: Creating Engaging Teaching Materials
🌳Parser Visualization
Flag this post
Albany Institute of History & Art, Developmental English Lexicon Project, Jaxsta Closure, More: Saturday Afternoon ResearchBuzz, November 22, 2025
researchbuzz.me·16h
🔍Tokenizers
Flag this post
Introspection in LLMs: A Proposal For How To Think About It, And Test For It
lesswrong.com·21h
⚖️Inference Rules
Flag this post
SDA: Steering-Driven Distribution Alignment for Open LLMs without Fine-Tuning
arxiv.org·2d
🔍ML Language
Flag this post
YASA (Yet Another Static Analyzer)
🔍Static Analysis
Flag this post
I built a task system that survives Claude sessions and works across any AI tool - entirely made with Claude Code
💬Interactive REPLs
Flag this post
Multidimensional Rubric-oriented Reward Model Learning via Geometric Projection Reference Constraints
arxiv.org·2d
🔍ML Language
Flag this post
New preprint: Apparent continuity & “self” in LLMs without any memory or hidden state – 71 downloads in 5 days (78 % view-to-download)
🎯Finite Automata
Flag this post
Automated High-Throughput Functional Protein Screening via Graph-Neural Network Enhanced Microfluidics
📋JSON Parsing
Flag this post
Taming the Data Beast: Build Pipelines That Bend, Not Break by Arvind Sundararajan
📋JSON Parsing
Flag this post
Personal Partial Evaluation: Clojure/Conj 2025
clojurecivitas.github.io·2d
🔗Concatenative
Flag this post
July 2024 Welcome Edition
lesswrong.com·2d
🔄Nanopass
Flag this post
Building Tornago: A Go Library for Tor Integration Born from Fraud Prevention Needs
🌍Minimal HTTP
Flag this post
What is the most modern way to implement traits/multiple dispatch/multiple inheritance?
🦀Rust Macros
Flag this post
Build your own cursor
💬Interactive REPLs
Flag this post
Models not making it clear when they're roleplaying seems like a fairly big issue
lesswrong.com·1d
🎲Parser Fuzzing
Flag this post
Loading...Loading more...