Initial impressions of Claude Fable 5
Initial impressions of Claude Fable 5
Initial impressions of Claude Fable 5
Flat Datacenter Networks at Scale The research roots of finding “optimal routing” networks trace back to the late 1970s. Mathematicians defined special kinds of networks called “expanders“. These are graphs with strong connectivity properties guaranteeing no subset of vertices can be isolated from the rest. In 1976, Leslie Valiant gave one of the earliest discussions
A new era for software testing Automatic programming dramatically speeds up writing software in certain use cases and in the right hands. In my experience the output does not reach the structural quality and economy of complexity of the best hand-written software. However, not all the software is stellar, and my feeling is that automatic programming
Thoughts on starting new projects with LLM agents
Running Python code in a sandbox with MicroPython and WASM
I tested every IP KVM in my Homelab Since the PiKVM came out in 2017, there’s been an explosion of IP KVMs. I’ve tested almost every one. But what are they good for? You can use Remote Desktop, Screen Sharing, or VNC to remote control a computer from anywhere on a LAN. And if you don’t have a private
On hope The comments on my previous post, on recent AI breakthroughs in solving Erdös problems and beyond, must’ve set some sort of record for the number of separate reasons commenters offered me to despair about the future of humanity. All this in a post that I saw as relatively nerdy and
Dropping to blog level In which I re-learn the need to balance writing and building.
Its hard to justify buying a Framework 12 My nephew just graduated high school, and wants a laptop. When he decides what computer to buy, price (or more precisely, value) is the most important attribute. Apple’s MacBook Neo upended the ‘value laptop’ equation—Apple’s not supposed to be both the cheapest option and the best value… but it seems like
Claude Opus 48 a modest but tangible improvement