» Tag
machinelearning
75 postsIn-House LLM Serving at Netflix: Design and Implementation
Netflix runs LLMs in-house, discussing key decisions on model deployment and API design.
Bonsai 27B Runs Locally on iPhone - A 27B Model in 3.9GB
Bonsai 27B model is developed with 1-bit quantization for local iPhone use.
LLM Evaluators Exhibit Bias Across Languages
Research shows LLM evaluators are biased in multilingual contexts, favoring lower-resource languages.
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.comThe True Cost of Kimi K3: $15 Output Price Isn't the Whole Story
An in-depth analysis of Kimi K3's pricing and parameter usage.
Evaluating Memory Frameworks: File, Vector, Graph, and RL Approaches
The evaluation shows that structured memory systems outperform file-based ones in accuracy and token cost.
Writer's Palmyra X6 Model Cuts AI Agent Costs by 52%
Writer announces Palmyra X6, cutting AI agent costs by 52%. Discover the model's impact and advantages.
AdaMAST: Adaptive Failure Taxonomies for Enhancing LLM Agents
AdaMAST is a taxonomy system that analyzes and improves LLM agent failures.
WISP: A CUDA Engine for Streaming 744B+ Parameter MoE Models on Consumer Hardware
WISP is a CUDA engine for streaming 744B+ parameter MoE models on consumer hardware.
Evaluating General-Purpose Robot Policies for Real-World Use
Explore the challenges in evaluating robot policies and the RoboLab solution.
Grabette: An Open System for Recording Robot Manipulation Data
Grabette is an open system for quickly recording robot manipulation data. Users can collect data easily with just a gripper.