» Tag
machine-learning
163 postsTrillion-Parameter RL Paper: Allowing the Model to Discover Workflows
The Ring-Zero paper explores a trillion-parameter RL model's ability to discover workflows autonomously.
Empero AI Launches Qwythos-9B-v2: Looping Issues Resolved and Robustness Enhanced
Empero AI's Qwythos-9B-v2 resolves looping issues and enhances robustness, offering a 1M-token context for advanced applications.
Self-hosting GLM-5.2 on a 4-node DGX Spark Cluster
Deploying GLM-5.2 on a 4-node DGX Spark cluster offers engineers a powerful self-hosting solution.
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.comI trained a 113M-parameter earthquake LLM from scratch
A 113M-parameter earthquake LLM was trained from scratch. The entire process is explained step by step.
Open-Sourced AI Agent Framework: Character, Rules, and Tool Creation
OpenSymphony is an open-sourced AI agent framework that governs agent identity and decision-making processes, offering secure and consistent AI experiences.
Multimodal Models Fail at Sampling, Not Understanding
Multimodal models aren't bottlenecked by capability but by sampling defaults—frame rate, chunking, cropping—that silently limit what they perceive.
Why Image Cleanup and Inpainting Fail at Scale
Why do soft edges, texture mismatches and visible seams appear in image editing pipelines? An architectural breakdown of mask dilation, context encoding and synthesis layers.
Don't Let the LLM Speak, Just Probe Its Hidden State
LLMs already encode the answer in hidden states before generating text. A tiny probe turns this into fast, cheap, calibrated zero-shot classifiers without generation.
Netflix Unveils Slow-Fast Architecture for Notifications
Netflix built a hierarchical notification system inspired by Kahneman's fast/slow thinking model, decoupling long-term pacing strategy from real-time message selection.
Your AI Agent Is Gaslighting Itself: Multi-Agent Solutions May Cost 15× More
Explore the bug of self-gaslighting in AI agents and the costs of multi-agent solutions.