YHacker Newsscreenshots

HyperNetworks arxiv.org ↗

A line of research where one neural network generates the weights of another, popularized by Google Brain in 2016.

OtherAI & MLweight-generationneural-networksresearch

Screenshot of arxiv.org, HyperNetworks's site

Captured 3 Nov 2026

Recommended in 1 thread

Astra can read and write weights to improve Qwen
rikiyat.github.io · 11 days ago
Recommended as the established foundation for models producing or editing weights.

Similar tools

Perplexity ↗AI & ML
An AI-powered answer and search engine.
1 thread
BERT ↗AI & ML
Google's 2018 bidirectional encoder Transformer model for language representation.
2 threads
neuron-explorer ↗AI & ML
A project for exploring and steering individual neurons in language models.
1 thread
Loom ↗AI & ML
A tiny custom neural network that executes programs, described in an arXiv paper.
1 thread
Gemma 4 AI & ML
Google's family of small open-weight models with quantization-aware variants.
3 threads
HY-World 2.0 ↗AI & ML
Tencent Hunyuan's open-weights world model for generating explorable environments.
1 thread
DeepSeek Harness ↗AI & ML
DeepSeek's coding agent harness.
1 thread
torch-neuronx ↗AI & ML
AWS's PyTorch backend for Trainium and Inferentia chips.
1 thread

Also in AI & ML

OpenRouter ↗
A marketplace that routes API requests to many LLM inference providers.
19 threads
DeepSeek ↗
A family of large language models offered via a low-cost API.
12 threads
llama.cpp ↗
A C/C++ engine for running LLMs locally.
12 threads
GLM ↗
An open-weights large language model family from Zhipu AI.
11 threads
Qwen ↗
Alibaba's family of open-weight large language models.
9 threads
DeepSeek V4.1 Flash ↗
A low-cost DeepSeek language model available via API.
8 threads
Artificial Analysis ↗
A site benchmarking and comparing AI models on quality, price and speed.
7 threads
Claude ↗
Anthropic's AI model and command-line assistant.
7 threads
Qwen 3.8 Flash Next ↗
A Qwen open-weight model that can be run locally.
5 threads
Strata ↗
An open-source project for running large MoE models on small-VRAM GPUs with system RAM.
5 threads
OpenCode Go ↗
A subscription plan for accessing models through the OpenCode coding tool.
4 threads
Pangram ↗
A service that uses a trained model to detect AI-generated text.
4 threads

Link from a commenter, not checked or endorsed by us: ↗ https://arxiv.org/pdf/1609.09106