💡 AI Reasoning - yfff · Scour

BendersLib: A Benders Decomposition Library in Python 📐Linear Algebra

news.ycombinator.com·2d·Hacker News

To Dissect a Mockingbird: A Graphical Notation for the Lambda Calculus (1996) 📐Math

dkeenan.com·5d·Hacker News

Where Reasoning Breaks: Logic-Aware Path Selection by Controlling Logical Connectives in LLMs Reasoning Chains 💬LLMs

The AI engineering stack we built internally 🕵️LLM Agents

blog.cloudflare.com·5d·Hacker News

GPU vs CPU Inference: 5 Scenarios, Real Costs & Latency 💾Retro Computing

tildalice.io·1d

The monstrous number sequences that break the rules of mathematics 📐Math

newscientist.com·1d·Hacker News

auditable inference runtime in Rust (BERT runs today) 🦀Rust

coelanox.com·6d·Hacker News

DeepSeek-V4 Can Hold Your Entire Codebase in One Context Window and It's Open Source 💬LLMs

firethering.com·1d·Hacker News

Closing the Loop: Running the Whole Agent Stack Locally 🦀Rust

mihaichiorean.com·3d·Hacker News

DeepSeek’s Sequel Set to Extend China’s Reach in Open-Source A.I. 🐙Open Source

·1d·Hacker News

Anthropic Introduces Managed Agents to Simplify AI Agent Deployment 🕵️LLM Agents

Rcarmo/gte-go: Golang inference for the GTE Small embedding model 🧠LLM

github.com·7h·Hacker News

Your First API Call 🤖AI

api-docs.deepseek.com·1d·Hacker News

Google TPU 8i for Inference and TPU 8t for Training Announced 🧠LLM

servethehome.com·2d·Hacker News

Pioneer: Vibetune Your LLMs 💬LLMs

pioneer.ai·3d·Hacker News

DeepSeek V4 - almost on the frontier, a fraction of the price 💾Retro Computing

simonwillison.net·1d

Google unveils chips for AI training and inference in latest shot at Nvidia 🔥PyTorch

cnbc.com·3d·Hacker News

DeepSeek targets $20bn valuation to stop poaching of staff 🧠Machine Learning

·2d·Hacker News

Claude Cowork against your own cloud inference provider ✍️Prompt Engineering

claude.com·3d·Hacker News

Scalable AI Inference: Performance Analysis and Optimization of AI Model Serving 🤖AI

Log in to enable infinite scrolling