🤖 ai - x64k

My Notes on the Progression from Context to Prompt to Harness engineering in making GPT LLMs Useful: (TUESDAY) MAMLMs

🔍Reverse Engineering News Blog

braddelong.substack.com

··Substack

Neo-X7/Neo-AI: A fully offline AI assistant powered by Ollama. Stores and retrieves conversations using SQLite + LanceDB vector search. No cloud. No API keys. Runs entirely on your machine.

📦QEMU Code

github.com··DEV

Unsloth Gemma 4 QAT

📦QEMU

unsloth.ai·

Tales of an Ollama Honeypot (Part 3): More Traffic, More Findings

🦠Malware Analysis

posts.inthecyber.com·

local AI agents for Cursor with pre-tuned marketplace/commu

🦀Rust

locaible.com··Hacker News

How I benchmarked a 100% local RAG pipeline to 9/9 (zero API keys)

🔍Ghidra

buy.polar.sh··DEV

local llm on laptop 780M GPU using llama + gemma 4 qat

📦QEMU Blog

alper.bearblog.dev·

Why Spring Teams Don’t Need a Second Runtime for AI Agents

⚙️Virtual Machines

foojay.io·

LLM AI Chatbots are letting me down every single day

🐛Fuzzing

umrashrf.github.io··Hacker News

"AI" Is Eating Platform Monopolist Free Cash Flow, Not the World: CHART OF THE DAY

🦀Rust News Blog

braddelong.substack.com··Substack

NexusOS v2.0 – A zero-dependency pipeline streaming server chaos to Parquet

🔍Ghidra

huggingface.co··Hacker News

Running Qwen 35B MoE at 450k Context on a Single 32GB GPU

⚙️Systemd

local-llm.utop.workers.dev··Hacker News

WWDC 2026: Foundation Models (& Anarlog)

💻operating systems

skushagra.com·

When AI builds itself 👷, AI is not a line item 📝, local LLMs for agentic coding 🤖

☁️Virtualization

tldr.tech·

Arconia for Spring Boot: DevEx, Observability, Multitenancy, GenAI, Cloud Native

📦Sandboxing Code

arconia.io··Hacker News

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency

📦QEMU News Blog

blog.google··Hacker News

Microsoft just shared the frontier data engineering secrets

Using local LLMs for agentic coding

James Cameron Wrote The Greatest Anti-AI Scene In Movie History – Hollywood Should Take Note

Gemma 4 QAT on 10GB Laptop: Local AI with 6.7GB VRAM

My Notes on the Progression from Context to Prompt to Harness engineering in making GPT LLMs Useful: (TUESDAY) MAMLMs

Neo-X7/Neo-AI: A fully offline AI assistant powered by Ollama. Stores and retrieves conversations using SQLite + LanceDB vector search. No cloud. No API keys. Runs entirely on your machine.

Unsloth Gemma 4 QAT

Tales of an Ollama Honeypot (Part 3): More Traffic, More Findings

local AI agents for Cursor with pre-tuned marketplace/commu

How I benchmarked a 100% local RAG pipeline to 9/9 (zero API keys)

local llm on laptop 780M GPU using llama + gemma 4 qat

Why Spring Teams Don’t Need a Second Runtime for AI Agents

LLM AI Chatbots are letting me down every single day

"AI" Is Eating Platform Monopolist Free Cash Flow, Not the World: CHART OF THE DAY

NexusOS v2.0 – A zero-dependency pipeline streaming server chaos to Parquet

Running Qwen 35B MoE at 450k Context on a Single 32GB GPU

WWDC 2026: Foundation Models (& Anarlog)

When AI builds itself 👷, AI is not a line item 📝, local LLMs for agentic coding 🤖

Arconia for Spring Boot: DevEx, Observability, Multitenancy, GenAI, Cloud Native

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency