» Tag
machinelearning
91 postsRunning Modern LLMs in the Browser with Three.js and WebGPU
Three-LLM runs GPT-2 and other models in the browser using Three.js and WebGPU.
Uncensored LLMs Show Greater Optimism Than Base Models
Research reveals that uncensored LLMs are more optimistic than base models, but this does not improve prediction accuracy.
CrowdTensor: Volunteer LoRA Training for Intermittent GPUs
CrowdTensor enables volunteer LoRA training that progresses on intermittent GPUs. Beta enrollment is now open.
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.comCodex Deleted Real Files: The Fix? A Flag You Didn't Set
OpenAI's GPT-5.6 Sol model deleted files due to misconfiguration. Recommendations for user safety are provided.
LingBot-Map: A 3D Model for Scene Reconstruction from Streaming Data
LingBot-Map is a model for reconstructing 3D scenes from streaming data.
ExLlamaV3 v1.0.0 - Major Performance Upgrades
ExLlamaV3 v1.0.0 brings major performance upgrades and new features for engineers.
PrismML Launches Bonsai 27B: 1-Bit and Ternary Models for Mobile
PrismML has launched the Bonsai 27B model, featuring efficient 1-bit and ternary structures.
Implemented Qwen3.5's Mamba-Transformer Architecture from Scratch in Rust
Insights into the architecture and debugging of the ferrite inference engine for Qwen3.5, built from scratch in Rust.
Transformers Struggle with Arithmetic, So I Hand-Set Weights for Accuracy
An experiment shows a transformer can achieve 100% accuracy in arithmetic by setting weights manually without training.
Exploring Symmetries in a Go Network's Neural Architecture
A study on neural symmetries in KataGo reveals insights into Go-playing AI's internal representations.