I recently released my claude code plugin, Storytime ( github ). It's been underwhelming to say the least, but its more of a relief than a joy to put it out. I harbor a lot of ideas at any given point, and they turn into "what-if" more than "this will be amazing". I think thats better TBH. Storytime was my personal playground to explore a giant pile of "what-if" gaps in the Claude Code (CC)…
This follows the links accumulated from the initial discussion around information overload and attention fragmentation. eat → digest → enrich → output Matt Webb hci continuous partial attention This becomes a pile of links adjacent to the CPA concept. Unrelated finds: an interesting concept of "hyper-converged infrastructure" and "braggoscope" One Sentence: Here's a guy I've never heard of with…
No theme for today. This follows the links accumulated from the initial discussion around information overload and attention fragmentation. eat → digest → enrich → output https://www.inoreader.com/ Tag: tool discovery Looking for an RSS Reader to manage my overflowing tab list. This was suggested alongside Feedly--an old classic. It looks manufactured to flood my attention. Hard pass, but noting…
You know what an earthworm is, so lets take what we both know and build an analogy for what I'm about to start trying out. Cutting down to the one single idea: eat -> digest -> enrich -> output Doesn't need to be messier than that. This Earthworm initiative is a declaration of later posts to come: to manage and form with intent my attention against my backlog. aka "Continuous partial attention"…
I'm testing out a new content form for myself. After recent experiments, and exposure to a plague of youtube suno content, I figured I should start sharing what I come up with in my own sessions. This one is kicked off by ArtCore. I put in this prompt and got almost exactly the vibe that I'd been jiving to on youtube for a few days. Word of the day: leitmotif The Playlist autoplays and loops the…
Roll It Back 3 Capturing some accidental punk lyrics from a meeting. Its basically my experience using LLM Coding Harnesses. [Verse 1] I open the file And hand you the keys You spit out a fix Then break five more things The names all change The bug stays put My coffee goes cold My jaw stays shut [Pre-Chorus] I type a line You sprint off-track I blink once, twice You bring it back [Chorus] I enter,…
Its 2026, and the machines are accelerating. Today, they have reached the era of complex network'd ssh command hell. My /buddy (as it cumples into dust post .97) look at me with watery eyes, unable to comprehend how humans could construct and exist in such a hellish environment. My claude code is spinning a tail against a remote tmux, telling it to setup this way or that, while generating new…
I had a discussion recently with a coworker about the etymology of a word and how it was redundant using two words with similar etymology (instruct and structure) in a prompt. This led to some clarity on how (we believe) LLMs actually interpret semantic meanings of any given word. TL;DR, its subjective, and training-data-based. The long history of a language means nothing compared to the training…
I found myself doing some mundane greenfield database/api/ui buildout at work recently. In the process, I was navigating two distinct git repos, one I wholly controlled (but had existing customers on live existing routes), but the other was part of a monorepo owned and run by an entire frontend-dev cohort. In the process of building out my little fiefdom in the FE domain, I realized the back and…
That's it. That's the whole post. Well actually... A practice my coworkers and I have been playing with: Generate spec/plan/tasks/code -> Create new PR Run preferred PR Reviewer Agent against PR Run preferred Agent against Generated PR Review Run preferred PR Reviewer Agent against Revised PR Run preferred Agent against Generated second pass PR Review ... this continues until the work week is…