🎖 Text Quality Models - hop1.ng.1357 · Scour

Fixing LLM Writing with Distribution Fine Tuning 📋Text Quality

rosmine.ai·2d·Hacker News

Training a 22MB prompt injection classifier 💉Prompt Injection

stackone.com·13h·Hacker News

Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection ✨LLMs

Scaling Real-Time Traffic Forecasting with a Graph-Aware Transformer ⚡Edge AI

uber.com·11h·Hacker News

SEOTrends scans the internet to uncover easy-to-rank SEO opportunities 🧭Content Discovery

seotrends.pro·2d·Hacker News

Liquid Harness — from zero to a fine-tuned LFM in under an hour 🤝Human-AI Collaboration

lqh.ai·5d·Hacker News

Show HN: Marlin-2B: a tiny VLM to extract structured information from videos ✨Gemini

huggingface.co·2d·Hacker News

gouravnagar-infosec/ai-kill-chain: A defender-side extension of the Lockheed Martin Cyber Kill Chain for LLM and agentic AI threats. Adds a model supply chain stage and splits actions-on-objectives into exfiltration, model extraction, and agentic pivot. 🕵️Threat Intelligence

github.com·22h·Hacker News

Context pruning: cut LLM tokens without losing quality (9 minute read) 🤖LLM

Employing Vision-Language Models for Face Image Quality Assessment 🖼️Multimodal AI

What political censorship looks like inside an LLM's weights — a mechanistic-interpretability study of Qwen 3.5 🤖LLM

vas-blog.pages.dev·2d·Hacker News

FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale ⚡Edge AI

frontier-cs.org·5d·Hacker News

AI Resist List 🛡️AI Security

airesistlist.org·7h·Lobsters, Hacker News

MinusPod self-hosted podcast ad remover learns from opt-in crowdsourced patterns 📡RSS

github.com·2d·Hacker News

rl for red teaming: training models to attack and defend themselves 🛡️AI Security

castform.com·6d·Hacker News

How Big Tech is harnessing the data of Indian factory workers to train robots 👁️Surveillance Capitalism

scroll.in·1d·Hacker News

The Ultimate LLM Fine-Tuning Guide ✨LLMs

promptinjection.net·3d·Hacker News

Precision Tracked Transformer via Kalman Filtering, Kriging and Process Noise 🛡️AI Safety

BuffaloTechRider/Autodidact: Self-learning AI agent that gets smarter and cheaper over time. Routes between local and cloud LLMs, learns from every interaction, remembers everything. ✨Gemini

github.com·1d·Hacker News

Benchmarking Subquadratic's latest model and SSA Kernel 📱Edge AI Optimization

appen.com·6d·Hacker News

Log in to enable infinite scrolling