We didn't rewrite our feed handler in Rust
databento.com·27m·
Discuss: Hacker News
🔒Rust Borrowing
A grand week
blog.mitrichev.ch·1d·
🧩Constraint Solvers
A Global Mining Dataset
tech.marksblogg.com·1d·
Discuss: Hacker News
📈Earley Parsing
Anthropic Says Claude Sonnet 4.5 Is World's Best Coding Model
i-programmer.info·19h
Gleam
GPU Clusters and LLM GPU Hosting: Powering the Future of AI Workloads
vibe.forem.com·8h·
Discuss: DEV
📋Tablegen
My PC Is Now Smarter Than Me
caffeinated.bearblog.dev·9h
📏Linear Memory
GPT Translator vs Google Translate: Which One Understands You Better?
dev.to·55m·
Discuss: DEV
🎮Language Ergonomics
Generative AI finds antimicrobial peptides against multidrug-resistant bacteria
nature.com·2d·
Discuss: Hacker News
🗺️Region Inference
LongCat-Flash-Chat: Powerful Open-Source AI for 2025
digitalocean.com·1d
💬Smalltalk VMs
Detecting Notational Errors in Digital Music Scores
arxiv.org·1d
🔍Text Indexing
Huawei's new open source technique shrinks LLMs to make them run on less powerful, less expensive hardware
venturebeat.com·3d
🔄Binary Translation
How Confident are Video Models? Empowering Video Models to Express their Uncertainty
arxiv.org·1d
Effect Inference
Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data
arxiv.org·9h
🗺️Region Inference
Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents
arxiv.org·9h
💬Interactive REPLs
Adventures on the AI Coding side of things
medium.com·1d·
Discuss: Hacker News
🎭Program Synthesis
LLMs are badly misaligned
lesswrong.com·1d
Type Checking
Farewell-to-Framework-Bloat-How-I-Rediscovered-Simplicity-Without-Sacrificing-Performance
dev.to·9h·
Discuss: DEV
📦Monorepos
A Study of Neural Polar Decoders for Communication
arxiv.org·1d
🪜Recursive Descent