Even if I use an automation (via n8n) for my Micro.blog timeline summarization, I still come here to read my timeline, although less frequently than before. It’s a good way to gauge how well or poorly LLM can be at summarizing such content. ☝🏻
I just updated my blog at meta.numericcitizen.me with my new design. The default view on the site is now dark mode, which includes a smooth visual animation.
Quoting Bryan Cantrill — Simon Willison
Work costs nothing to an LLM, and LLMs do not feel a need to optimize for their own (or anyone’s) future time, and will happily dump more and more onto a layercake of garbage.
Until recently, thanks to rising chip prices, human developers were too lazy to optimize their software stacks, leading to bloated software requiring much more memory than necessary to run. Now there is an incentive to rethink how they allocate development time, but it will probably be delegated to LLMs… we’re doomed.
M.G. Siegler about Apple’s AI competitiveness in Serious About Computing? You Should Build Your Own AI. — Spyglass
While they may look smart at some point for not pouring hundreds of billions into CapEx spend, that could come back to bite them in ways that are more tangential. Including, culturally, if the DNA of the company is never rewired to operate in the Age of AI. “People who are really serious about software should make their own hardware,” Alan Kay famously declared in 1982. What if the modern day version is something like: “People who are really serious about computing should make their own AI”?
I think we are still in the early days of generative AI. Siri’s failures apart, generative AI being so different than anything Apple did with Siri in the past, they can (and should) outsource their AI infrastructure. Eventually, they might bring it in, just like they did for Qualcomm modems, for example.
Forcing Micro.blog to rebuild the entire website to enable a design change is so slow; close to 30 minutes each time. 😳 One of the challenges is that not all design changes require a full rebuild; some do, some don’t, and I don’t always know in advance which ones do. Claude AI is not very good at predicting this either.
Probably one of the coolest images coming from the Artemis II mission. So cool.
Since returning from vacation yesterday, I’ve been using Claude Code for different things, and yes, I can confirm that the credit consumption rate is much higher than it was a few weeks ago. 😳
Trying to Define What is a Blog Home
This might be obvious for many bloggers, but these questions popped up in my mind this morning when working to enable the new visual design of my blog.
What is a blog’s home? Or is it defined? Should it be the geographical region where the blog is hosted? Or should it be the author’s regional location? Or should the author sign with his or her name followed by both, like “Numeric Citizen from Montréal, Canada, hosted on a server somewhere in the US”? And where this signature should go? At the end of each post? Or at the end of the blog’s main page?
I’m still pondering my options.
Announcing a New Blog Design
Finally, after so many years on Micro.blog, I’m excited to announce that this blog is now using my custom-built visual theme, built entirely with Claude AI, Claude Code, and a lot of my spare time. Bye-bye third-party visual plugin1! This marks a major milestone for me, as I have always wanted to have my own design for this blog2.