anhldbk
Gemini CLI Shake-Up: Abuse Controls and Traffic Priorities
Simon wrote an article "What is agentic engineering?" [1]
> Now that we have software that can write working code, what is there left for us humans to do? > The answer is so much stuff. > Writing code has never been the sole activity of a software engineer. The craft has always been figuring out what code to write. Any given software problem has dozens of potential solutions, each with their own tradeoffs. Our job is to navigate those options and find the ones that are the best fit for our unique set of circumstances and requirements
Such navigations may require various skills. For example: people/product skills (e.g customer empathy) to determine what to build, or engineering skills (e.g optimizations). Please be open for learning and get stronger via feedbacks.
[1]. https://simonwillison.net/guides/agentic-engineering-pattern...
Personal AI Infrastructure
Show HN: Beam – The most private way to share files
Ever needed to send a file to someone standing right next to you, but didn't want to use email or a cloud server?Check out Beam. It turns your screen into a data stream, allowing you to transfer files securely to another device using just your camera. It works completely offline, meaning your data never leaves the room.Simple, secure, and surveillance-free.Give it a try:...
Cap'n Web: A JavaScript-native RPC system
Beam is perfect for sharing sensitive documents, transferring files when you can't use USB, email, or cloud storage.
Try it here: https://get-beam.vercel.app
An Introduction to Virtual Consensus in Delos
Unison Lang: A big idea of content-addressed code
[1] SQL layer in FoundationDB, https://forums.foundationdb.org/t/sql-layer-in-foundationdb/...
NixOS and Flakes Book: An unofficial book for beginners
CommetBFT 1.0: Byzantine Fault Tolerant middleware for replicated state machines
LZ4 v1.10.0 – Multicores Edition
Pragmatic SRE
Securing Git: Addressing 5 new vulnerabilities
Tell HN: Happy Lunar New Year 2024, Year of the Dragon
For ollama, llama2:7b is 3.8 GB. See: https://ollama.ai/library/llama2/tags. Still I see ollama requires less RAM to run llama 2