@evnm · textlog

Wrote a short essay on the overreliance of metaphor in our "understanding" of the brain

Introduced an MCP server this morning for the app I'm working on (getonmain.com), based on a user request. Curious to see how/if folks use it.

Currently it provides a single read-only tool that lets agents fetch all the data in Main about the user's home (details about the home itself, systems/appliances, documents, any repairs they've logged). I think it could get interesting once we provide additional tools for logging repairs, upgrades, and more into the home's memory.

Compared to other apps which all build their own AI chat features, I wonder if the move could be to cede ground on this arms race and focus on building other features that add value for our users. Feels like a "commoditize your complement" situation.

Finally got around to setting up Remux on my phone so I can connect to tmux sessions when I'm not at my laptop. Even just for around the house, this seems like it'll be super useful.

Tell us more! What apps are you operating?

This is for monitoring/poking agentic coding sessions while I'm not at my computer. So, typically Claude, Emacs, and an overmind process running my app locally in different panes of a tmux window.

Call me old fashioned, but instead of adopting one of the "agentic coding orchestration frameworks" that seem to basically be reinventions of tmux, I've been tweaking my tried-and-true tmux-oriented workflow to incorporate agentic coding harnesses in an ergonomic way. I'm currently still using Claude Code, but getting Pi-curious as local models advance.

I will be dead, and many years will pass after that, before local models are capable to match those of the big companies, unless their intended use is banal.

It seems like we've reached a point where mid-grade frontier models like Sonnet are good enough for most day-to-day tasks. And Sonnet-grade models are already runnable on the higher end of consumer hardware. In which case, I can imagine a workflow where local models serve as workhorses for implementing plans that you may bump up to e.g. Opus or Sol to produce.

This seems reasonable and motivates my bias. But I don't know what to believe anymore.

Overvalued, maybe. Extremely valuable, yes, though.

For sure. We're well past the point of being able to reasonably claim that the tools have no practical use. But I share the article's skepticism that LLM-based AI will "produce a fully automated drop-in replacement for most knowledge workers". Which it at this point has to in order to justify these companies' stupendous valuations.

Tomorrow no but there will always be the “hope” which is enough for the next 20 years before giving up. Which meanwhile would be replacing larger and larger chunks of the workforce so it won’t really matter, we’ll be adjusting our lives around it as well so we meet in the middle.

Tesla has been overvalued for over a decade with the promise of “fully autonomous cars” and it’s still not losing its value, despite not meeting that (and probably never will, as the computation necessary to achieve it is bounded by physics).

That's a different situation. Tesla's a public company whose valuation is driven by the market, which has the right to be irrational. My understanding is that the AI buildout is financed such that the companies need to turn a profit by ~2030 or else they drown in capital costs.

Or maybe the frontier labs become Tesla-like, if it turns out investors just want to believe in the dream and don't care about financials that don't make economic sense. I just don't see that happening, given current sentiment and the overwhelming unpopularity of AI in the West.

Sigh. On the heels of , I just went into our garage to find a panel of insulation fallen to the ground, riddled with mouse droppings. 🤢😫 Cleaned it up (gloved and masked, naturally), but probably means we need to re-insulate the whole garage. Which will undoubtedly uncover a leak or some other issue. The fun never ends!

Obviously, I realize that it's a privilege to own a home and have issues like this to deal with 🧎‍♂️

This feels right to me. Or, if not right, then one of the safest strategies to remain employable as a software engineer.

Makes sense to me, though I think one important (IMO) aspect of this evolutionary role is incurring liabilities. Yes, software can be created by a wider audience, but when things go awry, would they have the aptitude or contingencies in place to recover and take responsibility?

Agreed. I think the AI hype underestimates the human factor in keeping medium-to-large organizations running.

The 2030 release date of StarCraft: Dominion is so extreme that it feels like an indictment not only of Blizzard but indirectly of AI

They’re owned by Microsoft, of all companies. If AI hyperproductivity is real at scale, then why can’t the game come out next year? Next month?

Gave this evergarden colorscheme a shot after seeing it on lobsters today. Quite liking it.

Also prompting me to refresh my tmux config, which I've been meaning to do for years now. ~~Spring~~End-of-Summer cleaning!

Cool use of ANSI sequences in curl -L evergarden.moe - can preview the theme without running any shell scripts!

But maybe we'd all be a little saner if we remembered what we're actually doing: building tools to make our lives and the lives of others easier.

This resonated a lot. I’m glad I read it now, before going totally insane lol. But I disagree that it’s just a glorified spreadsheet. The UI/UX matters, how you present the data, how they can change and so on, all of those things play a role. The good thing with AI is iteration is cheaper than ever, so you can experiment and process the results quickly. But yeah sometimes I just do things here because I just have to be doing something, I can’t leave it alone.

Agreed. The "just" makes the statement sound dismissive, but I do agree with the underlying sentiment that most software boils down to CRUD apps that help people organize information and complete tasks more efficiently. I think the path to developer enlightenment is realizing this truth without despairing over it.

“Mark all as read” isn’t working for me. I seem to be stuck at a baseline unread count of 11.

Cache invalidation, hardest problems in computer science. I’ll look into it.

Should be fixed now.

Yes! Thank you. Cache truly does rule everything around us.

I can't believe Apple fell for foldables

and an top of that, not calling it the iFold

i think theyre pretty cool. the tech market is too safe nowadays.

Totally, I'm glad they're at least trying something new (for Apple). It just underscores the general failure of imagination vibes I get from everything in tech nowadays. Most of the industry is breathlessly chasing a 20th century "golden age of scifi" vision of AI. And Apple's over there diligently trying to improve upon other companies' products from five years ago. At least no one's talking about the metaverse anymore.

yea its kind of sad how the design language has all converged to the same phones and laptops. 1990s/2000s tech had so much swag and fun with design, especially japanese brands. i like what nothing does, the uk smartphone brand. at least they have some identity. and yea the metaverse to my mind was just a meme eversince they introduced it, like I know exactly 0 ppl that own a vr headset, and im with the nerds here. just shows zuck is surrounded by yes men

🎯

Built a couple lambdas today to send account verification and onboarding drip emails for folks who sign up for my app but don’t make it all the way through the onboarding flow. Pretty cool to be able to quickly bang out self-contained infra for this instead of having to pay some SaaS vendor.

Friday Aperitivo: martini, a magazine, and a dog by my side

Lot of wildlife run-ins on my neighborhood trails this week. Ran past three deer yesterday, including a buck. Then a hare as I made it to the top of San Pedro Mountain this morning.

I laughed at this. I'm all for people crafting their own tools, but it really feels like everyone's reinventing the same handful of wheels for agentic development.

In terms of where I invest my time, I'm trying to find ways to zig while everyone's myopically zagging.

Is it intentional that post (and profile bio) character count is taken up by markdown formatting chars? I tried to add a link to my bio and was surprised that the URL ate into the character count limit.

Yes it can’t be done otherwise without introducing JS, the character limit is now against all content including that which hides.

Ah, got it. Thanks for the reply.

Maybe it’s a bit short. I’ll make it longer, ~~250~~ 300 chars.

Nice, that seems like a good change. Thanks!

Now it’s 300 chars! The links should fit now.

I just hit the 4xx ratelimiting page. Guess I'm too powerful a user today 😅 However, I turned off Cloudflare WARP and am back to posting. I wonder if they use a shared IP pool and other WARP users are on here.

Watching the UTMB livestream. Any other trail fans out there tuning in?

Preparing for opening up an app I'm working on for a public beta. Main is a quiet app that helps you maintain the value of your home:

Looks great! Nice job! reveal“I think my house is haunted” 🤣 — the blank og image scared me for a bit also :p

hahaha you're the first person to call out that easter egg I threw in 😆

What blank og image? textlog doesn't render og meta previews, right?

it does, when you hover links on desktop only. And there is a comment in the source you left that says it’s there to allow crawlers to process it without doing a page screenshot.

Ah, yes. Had focused on og meta text for iMessage previews, but still had a blank image for og:image. Lemme address this now. Thanks for mentioning!

ok, have a nice new og:image. The link in my original post in this thread still shows an empty preview. Looks like you download and re-serve the og:image files in textlog.

Yes the og is downloaded and re-served, to avoid leaking/tracking of client information. You need to edit and save to refetch, I did it for you now.

Oh nice, thanks!

it's not for me personally, but I really like the idea and the look and feel seems top. Good luck.

Opened up signups and about on LinkedIn yesterday. Really strong response so far!

Congrats! 🎉

Good luck!

One benefit of everybody freaking out about the death blueberries is that blueberries are cheap for the rest of us rn

join the communityorbrowse more notes