ML-assisted Data Structures, Neural Networks, B-tree Replacement, Database Optimization

How the Growth of AI May Drive a Fundamental Step-Change in the Domain Name Landscape
circleid.com·10h
📡DNS Archaeology
An enough week
blog.mitrichev.ch·7h·
📈Linear programming
Teaching Models to Decide When to Retrieve: Adaptive RAG, Part 4
blog.reachsumit.com·3d·
Discuss: Hacker News
🧠Learned Indexing
The effective LLM multi-tenant security with SQL
getbruin.com·7h·
Discuss: Hacker News
🗄️Database Internals
Three Solutions to Nondeterminism in AI
blog.hellas.ai·1d·
Discuss: Hacker News
🎯Performance Proofs
Automated Copyright Infringement Detection via Semantic Fingerprinting and Dynamic Thresholding
dev.to·1d·
Discuss: DEV
👁️Perceptual Hashing
LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval
arxiv.org·23h
📊Learned Metrics
Beyond Vector Search: Building a RAG That *Actually* Understands Your Data
dev.to·14h·
Discuss: DEV
🗂️Vector Databases
Getting a Hypergraph of Functions to a Browser
systeminit.com·10h·
Discuss: Hacker News
📐E-graphs
TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning
arxiv.org·23h
🔨Compilers
Inverse Mixed-Integer Programming: Learning Constraints then Objective Functions
arxiv.org·2d
📈Linear programming
How well can large language models predict the future?
forecastingresearch.substack.com·7h·
Discuss: Substack
📈Time Series
Show HN: Using an LLM to sensibly sort a shopping receipt
treblig.org·14h·
Discuss: Hacker News
🔗Constraint Handling
Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
arxiviq.substack.com·17h·
Discuss: Substack
💻Local LLMs
Beneficial Reasoning Behaviors in Agentic Search and Effective Post-training to Obtain Them
arxiv.org·23h
🔍Semantic Search
Making GitHub Issues Search Suck Less with BigQuery, Vertex AI and CloudQuery
cloudquery.io·14h·
Discuss: Hacker News
🌐Federated Search
I played 1k hands of online poker and built a web app with Cursor AI
blog.rchase.com·1d·
Discuss: Hacker News
🚀Indie Hacking
Tiny AI model outperforms o3‑mini and Gemini 2.5 Pro in ARC‑AGI benchmark
the-decoder.com·12h
🧠Intelligence Compression