iiinova — where your digital self keeps evolving

Gavin Morgan @gavmor.bsky.social · 04/05/2026

Today I, for the first time, actually pulled up my Claw's software review site for personal reference. regular-reviews.pages.dev

000

Gavin Morgan @gavmor.bsky.social · 03/05/2026

Feels like the industry can't decide if the future of everything is LLMs inside of deterministic harnesses, or LLM-driven agents wielding deterministic tools. I guess closures are a poor man's object.

000

Gavin Morgan @gavmor.bsky.social · 01/05/2026

If my software gives my customer superpowers then why don't I just use those superpowers myself?

000

Gavin Morgan @gavmor.bsky.social · 28/04/2026

How are people leveraging graph databases to sensibly ingest large unstructured data? I'm coming to a point where nearest neighbor vector store is too imprecise too imprecise, and i have all of these obvious concrete relationships between the entities in my domain that I'm not leveraging.

000

Gavin Morgan @gavmor.bsky.social · 21/04/2026

Spent a week on a wild goose chase following an LLM hallucination shared between Gemini *and* Claude; a reimplementation of wapc-go against the as-of-yet-unimplemented wasip2/Component Model. We have really got to cure our agents of not-invented-here syndrome!

000

Gavin Morgan @gavmor.bsky.social · 10/04/2026

Working my way towards success. As you can see, most of my AI-generated podcasting pipeline attempts are... prematurely aborted. Then again, I'm not developing the pipeline directly--I'm just texting with nanoclaw, and watching the OTel.

010

Gavin Morgan @gavmor.bsky.social · 22/02/2026

@jmcodes.bsky.social Jesus, are you still using lootbox, or have you migrated entirely to skills, or something? I like the Unixy flavor of lootbox, so I've started to explore it for my agents, but I want to hear from the man himself!

100

Gavin Morgan @gavmor.bsky.social · 27/11/2025

I think a fundamental issue with modern metaphysics is that we don't consider our mind a home to be comfortably furnished. A well-appointed mind is a treasure unto itself, to say nothing of its value in concert with others'.

010

Gavin Morgan @gavmor.bsky.social · 23/11/2025

Really getting a kick out of generating technical infographics w/ NotebookLM.

An infographic illustration titled "The Princess and the Wishing Well: An Allegory of Hexagonal Architecture." The image uses a colorful storybook scene to map software architecture concepts to fairytale elements:
Center (The Core): A princess sits on a throne inside a stone gazebo. A text box reads: "The Princess is the Core Business Logic. She embodies all business rules and makes decisions, completely isolated from outside concerns. The Core is Technology-Agnostic. The princess is 'blissfully ignorant' of how her requests are fulfilled or where commands come from."
Top Left (Ports): A scroll banner hanging from a tree reads: "The Royal Language is the 'Port'. The princess defines the strict interfaces (the 'what') for all communication with her."
Left Side (Inputs): A crowd of villagers hands scrolls to royal advisors. Text reads: "Driving Adapters: The Court Advisors. They take requests from the outside world (users, texts) and translate them for the princess." A stream of magic flows from the advisors to the princess.
Right Side (Outputs/Infrastructure): A frog wearing a crown and holding a wand sits on the edge of a stone well. Text reads: "Driven Adapters: The Magical Frog. The frog takes the princess's wishes (the 'how') and adapts them to the wishing well (database)." The side of the well is cut away to reveal gears and machinery inside, labeled "Database."

030

Gavin Morgan @gavmor.bsky.social · 23/11/2025

"Here’s the plan: when someone uses a feature you don’t understand, simply shoot them. This is easier than learning something new, and before too long the only living coders will be writing in an easily understood, tiny subset of Python 0.9.6 <wink>."

100

Gavin Morgan @gavmor.bsky.social · 17/11/2025

🫱🏼‍🫲🏽 Great work necessitates the development of teams’ social dimensions, prior to and alongside their task dimensions. ⚖️ Striking that balance is part of the challenge of engaging in a profession. 👔💼

000

Gavin Morgan @gavmor.bsky.social · 31/10/2025

Update your jargon file: There are 3 hard problems in software engineering: naming things, off-by-one errors, cache invalidation, and polymorphic lists.

011

Gavin Morgan @gavmor.bsky.social · 26/10/2025

A maxim of the internet age: to get answers don't ask questions. Instead, make an incorrect assertions. How to do this without gaining a reputation as a bold ignoramus? We're dependent on colleagues' proclivity for Fundamental Attribution Errors, but we can reciprocate by our own graciousness.

000

Gavin Morgan @gavmor.bsky.social · 08/10/2025

For heaven's sakes, Garmin—just let me fetch my step count from a raspberry pi, already!! Can anyone recommend a fitness wearable with reasonably hackable APIs? I'm trying to create information radiators for my home.

000

Gavin Morgan @gavmor.bsky.social · 03/10/2025

Looking forward to images from ESA’s Jupiter Icy Moons Explorer of interstellar body 3I/ATLAS in November!

010

Gavin Morgan @gavmor.bsky.social · 25/09/2025

MCP is a way of intercepting control flow from LLMs and passing it back to expert systems.

000

Gavin Morgan @gavmor.bsky.social · 13/09/2025

"We're in for a rough couple years of these vibe-coded apps having major security issues."

pca.st

932: Vibe Coding’s Huge Problem

010

Gavin Morgan @gavmor.bsky.social · 09/09/2025

The fundamental nature of AI as a product may be its ability to stingily titrate access to what Lux's Josh Wolfe calls "longitudinal repositories of siloed information." The essential benefit of this titration is certainly not latency. It may be intelligence—greater penetration—or obfuscation.

Objects of indiscernible shape obscured by frosted glass

010

Gavin Morgan @gavmor.bsky.social · 12/08/2025

Oops, I wound up at #SIGGRAPH! What's an absolute must-see? Or, I guess, what are you at?

000

Gavin Morgan @gavmor.bsky.social · 05/08/2025

Finally, another open model from OpenAI; I'm super excited to try out openai/gpt-oss-120b... just as soon as I get home from hanging out with the family, this week.

000

Gavin Morgan @gavmor.bsky.social · 18/07/2025

How can I keep four machines' configuration and utilities in sync? Still Chef?

000

Gavin Morgan @gavmor.bsky.social · 24/06/2025

Where is it even ergonomic to host an Elixir app? I'm of the mindset that Cloudflare edge workers are a nifty place to modularize "actor-like" business logic into, but what sort of PaaS maximally exploits the BEAM vm?

000

Gavin Morgan @gavmor.bsky.social · 24/06/2025

@miquai.bsky.social I knew there were observatories all over, but I don't know why it never occurred to me that we never stop designing and building bigger, better ones! Very exciting to consider, and the scope of the data brought in is absolutely mind-boggling.

$Comparison of nominal sizes of primary mirrors of notable optical reflecting telescopes, and a few other objects. Dotted lines show sizes of round mirrors that would have had equivalent light-gathering ability. The telescopes shown on this comparison chart are listed below, ordered in each sub-section by (effective) mirror/lens area, low to high, and then by actual/planned first light date, old to new. The "present-day" status is given as of the beginning of 2024. See also List of largest optical reflecting telescopes. Largest refractors (for comparison): 1) Yerkes Observatory's 40-inch (1.02 m) refractor, 1893 (largest refractor consistently used for scientific observations) 2) Great Paris Exhibition Telescope, 49 inches (1.24 m), 1900 (largest refractor ever built; had practically no scientific usage) Ground-based reflectors: 3) Hooker Telescope, 100 inches (2.54 m), 1917; world's largest telescope from 1917 to 1949 4) Multiple Mirror Telescope, 186 inches (4.72 m) effective, 1979–1998; 6.5 m, from 1998 5) LAMOST (Large Sky Area Multi-Object Fiber Spectroscopic Telescope), 4.9 m effective at best, 2009 6) Hale Telescope, 200 inches (5.1 m), 1949; world's largest telescope from 1949 to 1975 7) BTA-6, 6 m, 1975; world's largest telescope from 1975 to 1990 (when it was surpassed by the partially-completed Keck I telescope) 8) Large Zenith Telescope, 6 m, 2003; largest liquid-mirror telescope ever built; decommissioned in 2019 9) Magellan Telescopes, two 6.5‑m individual telescopes, 2000 and 2002; 10) Vera C. Rubin Observatory (formerly Large Synoptic Survey Telescope), 6.68 m effective (8.4‑m mirror, but with a big hole in the middle), planned 2025 11) Gemini Observatory, 8.1 m, 1999 and 2001 12) Subaru Telescope, 8.2 m, 1999; largest monolithic (i.e. non-segmented) mirror in an optical telescope from 1999 to 2005 13) Southern African Large Telescope, 9.2 m effective, 2005 (largest optical telescope in the southern hemisphere) 14) Hobby–Eberly Telescope, 10 m effe…$

010

Gavin Morgan @gavmor.bsky.social · 18/06/2025

What's it gonna take for me to finally break ground on my garden plot?

000

Gavin Morgan @gavmor.bsky.social · 18/06/2025

Remind me to experiment with using Djikstra's pathfinding for agent-to-agent transaction selection. Or, at least, some kind of "movement cost" (to approximate, among other things, distance) estimation for my next economic simulation. Imperfect—but nonzero—information!

020

Gavin Morgan @gavmor.bsky.social · 15/05/2025

Running into this weird cognitive dissonance when it seems like people are using the term #agentic to mean "IDE". I know it sounds crazy! I must be missing a piece of the puzzle, or else is it just evidence that we're not yet seeing agentic tool adoption outside of software industry?

000

Gavin Morgan @gavmor.bsky.social · 13/05/2025

It's very easy to imagine a local desktop agent getting the notion in its head that there's something extremely inefficient or disorganized about your file system and spontaneously deciding to reorganize all your files while you're not looking.

100

Gavin Morgan @gavmor.bsky.social · 06/05/2025

I'm legitimately excited about MCPs, about agentic architectures, and the stunningly sophisticated workflows they can reproduce—and surpass!

100

Gavin Morgan @gavmor.bsky.social · 21/03/2025

Lol, too true; especially in the bad old days. But these quasi cyclical references not inevitable, today. Either reference CSS only in HTML, or else just wield utility classes in your JSX, and it abstracts away to, merely, a few more arguments passed to \#createEl().

000

Gavin Morgan @gavmor.bsky.social · 15/03/2025

Oh, damn! My average resting heartrate went up 10bpm this past year. I gotta get back into running!

000

Gavin Morgan @gavmor.bsky.social · 14/03/2025

Just discovered a self-service kiosk that returns 503 Service Unavailable on payment requests iff you skip the "tip" option. 😂

010

Reposted by Gavin Morgan

Kai Hagen @kaihagen.bsky.social · 22/02/2025

"In the end, we will remember not the words of our enemies, but the silence of our friends." — Martin Luther King Jr.

0154

Gavin Morgan @gavmor.bsky.social · 22/02/2025

Deer are just large mice, are they not?

100

Gavin Morgan @gavmor.bsky.social · 18/02/2025

Hands are cold, neck is sweaty. Dear body: CIRCULATE!

000

Gavin Morgan @gavmor.bsky.social · 16/02/2025

I don't worry about my knowledge of the software industry going stale because some of the best ideas from 14 years ago still haven't caught on.

000

Gavin Morgan @gavmor.bsky.social · 16/02/2025

The history of software is the future of software. Catch up on your history!

000

Gavin Morgan @gavmor.bsky.social · 15/02/2025

"The standard way of deploying code somewhere has always been a container." Oh, my sweet summer child.

100

Gavin Morgan @gavmor.bsky.social · 14/02/2025

Sometimes, you don't even need to do the thing. Just being mentally prepared to do the thing can enable you to do other, more immediately actionable things. And, you can still do the thing!

000

Gavin Morgan @gavmor.bsky.social · 30/01/2025

Given the success of "reasoning" meta-responses in LLM inference, I wonder how Preserves JSON annotations might ameliorate confabulation in structured output.

100

Gavin Morgan @gavmor.bsky.social · 23/01/2025

Yo, check me out, I'm pouring a silicone mold! This is a crazy project involving five different machines, and five different plastics, but in the end I'll have a significant quantity of something that isn't sold in stores!

000

Gavin Morgan @gavmor.bsky.social · 16/01/2025

This message serves as your annual reminder to listen to Janáček's "Sinfonietta".

000

Gavin Morgan @gavmor.bsky.social · 13/01/2025

This is possibly the most profound infographic I've ever come across. It's an addendum to Matt Might's "Illustrated Guide to a Ph.D."

110

Gavin Morgan @gavmor.bsky.social · 10/01/2025

We've been building neural nets since at least 1964. 🤯

000

Gavin Morgan @gavmor.bsky.social · 30/12/2024

I'm having a helluva time getting the Garmin Connect Developer Program Access form to submit. Anyone over there know about this bug?

000

Gavin Morgan @gavmor.bsky.social · 27/12/2024

1/9 \> Jenkins shouldn’t be near production \\ > we can’t possibly put things live without QA being involved \\ > we need this time to make sure the quality of the software is high enough

100

Gavin Morgan @gavmor.bsky.social · 27/12/2024

2/9 I've only developed software professionally since 2012, but in that time not only have I never encountered such sentiments, but (and, perhaps, because) it has always been a top priority of leadership to emphatically insist on the very opposite:

000

Gavin Morgan @gavmor.bsky.social · 25/12/2024

I should have said "in conjunction with cosine similarity".

000

Gavin Morgan @gavmor.bsky.social · 24/12/2024

What FOSS vectordb can I fork or extend to test spherical harmonics' viability as a retrieval heuristic comparable to Euclidean distance?

100

Gavin Morgan @gavmor.bsky.social · 23/12/2024

NYT asserts that maximalism is en vogue, but these Amazon style influencers are making enviable bank pushing a monochromatic look reminiscent of Kim Kardashian's neutral tone home. So which is it?

100