Do Nothing
blog.tanyakhovanova.comยท57m
ฮปLambda Encodings
YouTube gets ~5% CTR lift on Shorts by replacing embedding tables with Semantic IDs
shaped.aiยท2d
๐Ÿ“ŠFeed Optimization
Replacing the Type Checker for the Swift Compiler
forums.swift.orgยท3dยท
Discuss: Hacker News
๐Ÿ’งLiquid Types
Evaluating Gemini 2.5 Deep Think's math capabilities
epoch.aiยท2dยท
Discuss: Hacker News
๐ŸŽฏPerformance Proofs
LLM Optimization Notes: Memory, Compute and Inference Techniques
gaurigupta19.github.ioยท6dยท
Discuss: Hacker News
๐Ÿ’ปLocal LLMs
Solving the wrong problem
ufried.comยท2dยท
Discuss: Hacker News
โšกIncremental Computation
Building an AI Internal Linking Plugin for WordPress
dev.toยท1dยท
Discuss: DEV
๐ŸŒ€Brotli Internals
Reviving Lost Tongues: AI-Powered Grammar for Language Preservation
dev.toยท4dยท
Discuss: DEV
๐ŸŒณContext free grammars
PLSEMANTICSBENCH: Large Language Models As Programming Language Interpreters
arxiv.orgยท5d
๐Ÿ’ปProgramming languages
I Built the Perfect Workflow and attracted some friends in the process
graemefawcett.caยท1dยท
Discuss: Hacker News
โšกProof Automation
LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval
arxiv.orgยท3d
๐Ÿ“ŠLearned Metrics
Comparing human and language models sentence processing difficulties on complex structures
arxiv.orgยท3d
๐Ÿ”—Parser Combinators
Ollama SDKs in Go: Overview and Code Examples
dev.toยท17hยท
Discuss: DEV
๐Ÿ”“Open Source Software
FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline
arxiv.orgยท3d
โšกPerformance Mythology
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.toยท2dยท
Discuss: DEV
๐Ÿ“ŠMulti-vector RAG
LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions
arxiv.orgยท2d
๐Ÿ”ฒCellular Automata
Responsible Vibe Coding
dev.toยท1dยท
Discuss: DEV
๐Ÿ“Code Metrics
Structured Cognition for Behavioral Intelligence in Large Language Model Agents: Preliminary Study
arxiv.orgยท4d
๐Ÿง Intelligence Compression
Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data
arxiv.orgยท3d
๐Ÿง Learned Indexes
Aligning Large Language Models via Fully Self-Synthetic Data
arxiv.orgยท3d
๐Ÿ”—Monadic Parsing