What is this?
This mirrors the Hacker News front page. Click on tags to filter / exclude. You can combine multiple tags.
Get these tags inside Hacker News itself with these open-source browser extensions for Chrome and Firefox
histre is a power tool for your knowledge. This is a demo of its auto-tagging feature. Learn about its other features here
How we index images for RAG
• www.kapa.ai
Taking the Training Wheels Off: Aligning LLMs Without Personas
• www.lesswrong.com
What is to be done about MGLRU?
• lwn.net
Liquid AI reveals 8B-A1B MoE trained on 38T
• www.liquid.ai
Even (very) noisy LLM evaluators are useful for improving AI agents
• www.tensorzero.com
Local LLMs perform better when you teach them to ask before they answer
• www.xda-developers.com
Testing MiniMax M2.7 via API on three real ML and coding workflows
• andlukyane.com
KV Sharing, MHC, and Compressed Attention
• magazine.sebastianraschka.com
Agora-1: The Multi-Agent World Model
• odyssey.ml
We let AIs run radio stations
• andonlabs.com
Critical Views on LLMs, Another Academic Reading List
• read.misalignedmag.com
UK sovereign LLM inference
• relax.ai
Building ML framework with Rust and Category Theory
• hghalebi.github.io
AI shouldn't have a meter. Unlimited tokens. Forever
• www.openmonoagent.ai
The Problem with "Mathematically Proven" Claims About LLMs
• webdirections.org
The Anti-Singularity
• www.lesswrong.com
Local AI needs to be the norm
• unix.foo
Teaching Claude Why
• www.anthropic.com