First screen, captured .
Looks similar
Context Language Models(arxiv.org)
164 points by emersonmacro | 44 comments
arXiv paper introducing Context Language Models, LLMs that natively manage their own context by treating it as an editable file, with benchmarks on agent tasks.
Related stories
Show HN: Building a web search engine from scratch with 3B neural embeddings(blog.wilsonl.in)
578 points by wilsonzlin | 97 comments
Wilson Lin's blog post describing how he built a web search engine from scratch in two months using 3 billion neural embeddings.
RWKV: Reinventing RNNs for the Transformer Era(arxiv.org)
318 points by ianbutler | 164 comments
arXiv paper introducing RWKV, a model architecture combining Transformer-style parallel training with efficient RNN inference via linear attention.
AI models can provably hide arbitrary capabilities(arxiv.org)
252 points by sbulaev | 118 comments
An arXiv paper showing AI models can embed encrypted neural network backdoors that provably hide arbitrary capabilities from elicitation-based safety evaluations.
Show HN: I trained a 125M model to autocomplete piano on-device(simedw.com)
533 points by simedw | 110 comments
Blog post describing training a 125M-parameter transformer that autocompletes MIDI piano performances in real time on an iPhone, covering representation, data cleaning, and DPO.
Show HN: Building a web server in assembly to give my life (a lack of) meaning(github.com)
382 points by imtomt | 205 comments
GitHub project ymawky, a static HTTP file server for macOS written entirely in ARM64 assembly using raw Darwin syscalls without libc.
Turning GLM-5.3-Flash into a Jev-like decision model(privatemode.ai)
116 points by flxflx | 50 comments
Privatemode AI blog post describing how to prompt GLM-5.3-Flash so its first output token gives a decision in a single forward pass, benchmarked against Jev and Laya.