Weeknotes #345 โ€” Bath full of bricks
andrewdoran.ukยท1d
๐ŸŽฏContent Recommendation
Culture, Language, and Generative Language Models
cacm.acm.orgยท4d
๐Ÿค–Grammar Induction
Umwelt
en.wikipedia.orgยท1d
โš™๏ธsystems theory
How Google Translate & ChatGPT Work: The Transformer, Unboxed
dev.toยท1dยท
Discuss: DEV
๐Ÿง Learned Codecs
AI as both authors and reviewers of research papers
openreview.netยท1dยท
Discuss: Hacker News
๐Ÿ”ฒCellular Automata
Improving Temporal Understanding Logic Consistency in Video-Language Models via Attention Enhancement
arxiv.orgยท23h
๐Ÿ“ŠLearned Metrics
Beyond the AI Hype: Guido van Rossum on Python's Philosophy, Simplicity, and Th
odbms.orgยท3hยท
๐Ÿ“ŠAPL Heritage
The Hidden Bias: A Study on Explicit and Implicit Political Stereotypes in Large Language Models
arxiv.orgยท23h
๐Ÿค–Grammar Induction
Show HN: Using an LLM to sensibly sort a shopping receipt
treblig.orgยท1dยท
Discuss: Hacker News
๐Ÿ”—Constraint Handling
METRICALARGS: A Taxonomy for Studying Metrical Poetry with LLMs
arxiv.orgยท23h
๐Ÿ“ŠHyperLogLog
I Built the Perfect Workflow and attracted some friends in the process
graemefawcett.caยท4hยท
Discuss: Hacker News
โšกProof Automation
Building the Reasoning Engine at Axiom
axiommath.aiยท7hยท
Discuss: Hacker News
โš”๏ธLean Tactics
OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
arxiv.orgยท23h
๐Ÿ’ปLocal LLMs
Refactoring: A way to write better Code
dev.toยท1hยท
Discuss: DEV
โš™๏ธOperational Semantics
Neural Networks from Scratch in Python: Simpler Than You Think
hamza.seยท6hยท
Discuss: Hacker News
๐Ÿ“ŠQuantization
To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
arxiv.orgยท23h
๐Ÿ“ŠLearned Metrics
MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
arxiv.orgยท23h
๐Ÿง Learned Codecs
๐Ÿง  Real-Time Smart Speech Assistant with Python, Whisper & LLMs
dev.toยท6hยท
Discuss: DEV
๐ŸŽ™๏ธWhisper
2025-10-10 # LLMs Are Transpilers
alloc.devยท1dยท
Discuss: Hacker News
๐Ÿ”„Language Evolution
LoRA Explained: Faster, More Efficient Fine-Tuning with Docker
docker.comยท1d
๐Ÿ’ปLocal LLMs