» Tag
machine-learning
185 postsOpen-ultra: A Self-Training LLM Routing Proxy
Open-ultra is a self-training LLM routing proxy that reduces costs while maintaining high output quality.
Qwen3.6-35B-A3B on 4× Intel Arc Pro B70: Achieving 200 tok/s
The Qwen3.6-35B-A3B model offers four optimized configurations with 4 Intel Arc Pro B70 GPUs, balancing performance and flexibility.
Code Repair Training Data Created and Evaluation Released
A new code repair dataset enables engineers to test accuracy, improving fix rates from 17% to 40%.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comDeveloping a Goal-Conditioned Minecraft Model
Pantograph is developing goal-conditioned robotics models using internet-scale video.
RAG Evaluation: Faithfulness, Context Recall, and Answer Relevance
RAGAs evaluation enhances AI systems' reliability by utilizing three key metrics: faithfulness, context recall, and answer relevance.
From a 48-hour PDF rabbit hole to a repeatable research pipeline
An engineer's 48-hour struggle extracting data from academic PDFs led to an automated, auditable research pipeline with measurable gains in speed and reliability.
The Expensive Model Was Cheaper: Six Lessons from an LLM Judge
Insights from the Rekall app reveal unexpected lessons in model selection and cost implications for engineers.
Sentry's New AI Model Cuts Issue Grouping Errors in Half
Sentry upgraded its AI-powered issue grouping model, cutting duplicate issue creation by 20% and halving the rate of incorrect merges in production.
Knowledge Distillation: New Methods to Enhance Scalability
New methods in knowledge distillation are reducing costs and enhancing scalability for large language models.
How JAX Shards a Computation Across a Mesh
Explore how JAX improves computation placement with Auto, Explicit, and Manual methods. Learn about their impact on correctness in this detailed overview.