» Tag
machinelearning
91 postsISNAD: Adapting Classical Verification into a Trust Layer for LLMs
ISNAD introduces a new trust layer for claim verification in multi-agent LLM systems.
You can now fine-tune my 3.96M-parameter TTS on your own voice or language
A new toolkit enables fine-tuning a 3.96M-parameter TTS model on your voice or language.
Field Guide to LLM-as-a-Judge: AI-Powered Evaluation Process
LLM-as-a-judge is an AI method that accelerates evaluation processes. Discover our detailed guide.
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 Trust Ceiling: The Invisible Limit on AI's Capabilities
The untrustworthiness of AI systems creates a trust ceiling that limits adoption and economic potential.
Zyphra Launches ZUNA1.1: An Apache 2.0 EEG Model for Variable-Length Inputs
Zyphra has launched ZUNA1.1, an EEG model supporting variable-length inputs from 0.5 to 30 seconds.
In-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.
The 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.
Skill-Guided Mining and Compilation of LLM Agent Traces
TraceCompiler mines LLM agent traces to create executable workflows with reduced API calls.