yup trading compute for memory basically
COMPUTING
-
Local LLMs Tutorial: Runtime Fundamentals Explained
By
–
new tutorial just dropped covering how local llms work and all the runtime fundamentals
-
Local LLMs 101: Understanding GPU Processing and Architecture
By
–
– local llms 101 – tired of guides that just tell you to run a script and call it a day?
– want to actually know what your GPU is doing, not just trust a black box?
– here's what really happens when you run a local LLM
– what gets loaded, why, and how it all fits together
– no -
The Switch That Controlled Early ARPANET Internet
By
–
This switch turned off 1/3 of the Internet. Or at least it did in the earliest days of ARPANET in 1970, where it controlled the key BBN node in Boston. For better or worse, it no longer works (I tried flipping it when I visited the company).
-
ARPANet: 58 Years of Computer Network Innovation
By
–
58 years ago, Larry Roberts presented his idea for an "ARPANet" for connecting multiple computers together across the United States. Full paper: https://
shorturl.at/6uMNq -
Cloud Platforms Marketing Inflates Simple CRUD Development Costs
By
–
It's not bad software It's great software actually But new devs have been oneshotted by billion dollars of marketing money from platforms as a service to complicate building simple CRUD money so they have to pay $10,000-$100,000 bills for hosting Similar to BigPharma
-
VibeKit: Secure Sandbox for Running AI Coding Agents
By
–
Run Gemini CLI, Codex, Grok and Claude Code in a secure sandboxes. VibeKit lets you run AI coding agents in Docker containers with secret redaction and real-time observability baked in. 100% offline, local, and Opensource.
-
Life comes at you, Cerebras partners with Nasdaq Exchange
By
–
life comes at you, etc. https://t.co/rjO22tKTtG
— Jordan Novet (@jordannovet) 3 octobre 2025life comes at you, etc. Cerebras (@cerebras) Cerebras 🤝 @NasdaqExchange — https://nitter.net/cerebras/status/1973498440849170830#m
→ View original post on X — @jordannovet, 2025-10-03 21:23 UTC
-
Generalized Parallel Scaling with Interdependent Generations
By
–
Generalized Parallel Scaling with Interdependent Generations
-
ChatGPT 2030: Energy Consumption of a Nuclear Power Plant
By
–
By 2030, ChatGPT could consume the equivalent of a nuclear power plant per week. Electricity is becoming the new oil. My article in Trends co-written with @dr_l_alexandre