@bender@twtxt.net Hehe thanks! 😅 Still gotta sort out some other bugs, but that’s tomorrows job 🤞

Nope that appears to be fixed 👌 (but there are other annoying bugs) – I think I should nuke half this crappy Javascript code we wrote years ago and start over 🤣

Let’s see if yarnd 0.15.1@115c1cd still has this dupe bug? 🐞

@xuu

@xuutxt.sour.is to answer your question, the Mentions view and the Mentions filter work a bit differently. The former looks at the pod’s entire cache for mentions of you, whilst the later only filters the current view
If that makes sense – It does beg the question of whether the “Mentions” view is needed at all, as its equivalent to /discover?f=mentionsme I think

@eldersnake@twtxt.net You able to grab a screenshot of the console (debug) of the request? 🙏 I can’t repro this locally 🧐

@eldersnake@twtxt.net Yup! Nig I’m the JavaScript. I plan to fix this tonight!

Test

@eldersnake@twtxt.net Oh that’s not right? Hmmm 🧐 Is this consistently reproducible? If so what does the browser console’s network tab say about the request and response hete (XHR)

@eldersnake@twtxt.net I couldn’t agree more! 🤣

@xuu@dev.txt.sour.is Yeah it’s not feature gated or anything.

Sorry you’ll have to forgive me, what’s different? 🧐

@slashdot@feeds.twtxt.net What the hell?! 😱 So these companies would prefer to continue to harm human health?! 🧐

The same company separately quoted over $7,000 to install an outdoor garden tap and plumbing for approximately 20m 😱

Just got a quote to fix a bathroom tap and hoses that are corroded for > $1,000 😱

@bender@twtxt.net @lyse@lyse.isobeef.org Soeey where?

@aelaraji@aelaraji.com LOL 🤣

@shreyan@twtxt.net Yhe default is 20ms AFAIK so the delay you’re seeing is the axtual request latency I think?

I haven’t found a good way to do the right style of “indicator” yet 😢

Help wanted! 🙏 I also broke two other features that require client-side JavaScript 🤦‍♂️

@bender@twtxt.net Good advice!

@bender@twtxt.net Not yet and you’re probably right 🤣 The last part is probably far fetched 😅

@tkanos@twtxt.net I have a different solution. I a) ban social media networks on the network b) educate them about the dangers and c) permit them to use Twtxt / Yarn.social when they’re older.

Oops sorry yeah I accidentally duplicated the image links and edited very late 😢

@shreyan@twtxt.net It is!

Couple of days ago I made a small patch to yarnd (this pod effectively runs main) that filtered out “inactive users”, hard-coded to be LastSeenAt > 90 days and not bother fetching feeds for anything they follow. This has had a dramatic impact on the resources used by this pod (twtxt.net) – See screenshtos.

Has anyone noticed anything? that is y’all that actually do use this pod 😅

Thanks ! I’ll see what happened later tonight 🤞

True 🤣

@aelaraji@aelaraji.com Haha glad to hear it 🤣 Speaking of which, how are you finding the SPA-like experience on twtxt.net?

Or is this /. post just badly written?! 🤔

@slashdot@feeds.twtxt.net Any way of opting out of this? I trust Apple (sort of) because it’s a closed ecosystem. If Apple continue down this path of developing an advertising platform (too late?) and sharing data with 3rd parties, I’m not sure if I can continue to trust Apple… 🧐

Hey @meff@yarn.meff.me 👋 You still around? Your pod looks like it’s still alive and kicking, but rather old 😅

The Valley of Code: htmx – This is a pretty great article on HTMX really, haven’t read it fully yet, but it vibes with how I feel about it and my own experiences so ar 👌

@bmallred@staystrong.run Why walk at a heart rate of 170?

👋 If y’all notice any weird quirks or UI/UX bugs of late on my pod, please let me know! 🙏 For those that have a Javascript enabled web browser will notice (hopefully) a SPA (single page app) like experience, even in Mobile! No more full page refreshes! All this without writing a single line of Javascript (let alone React or whatever) 😅 – HTMX is pretty damn cooL! 😎 #htmx

@bender@twtxt.net Better user experience if you have Javascript enabled. Instead of refreshing the entire page with extra bytes and backend processing that’s unnecessary, you effectively replace the part of the UI that needs changing with a partial response.

Mooaar HTMX support inbound for yarnd 👌

@bender@twtxt.net Hehe 🤣 There are still going to be small things to fix here and there but so far so good 🤞

I’m glad you keep me on my toes 🤣

@bender@twtxt.net Fixed 😅 Sorry about that! Updating rolling out shortly…

Oh I see what I’ve done, nothing to do with HTMX, just my bad ability to search the codebase. I thought podMenu wasn’t used or podLogo clearly not 🤣

@bender@twtxt.net Haha, what’s not working on mobile? 📱 Hmm? 🧐 I might have to revert all this HTMX code if it’s broken things that badly?

It’s a little awkward to use though, because you have to make sure you URL encode the uri 😅 That google drive feed was some URI!

$ bat POST "https://pod.domain.tld/api/v1/cache/delete?uri=$(pbpaste | urlenc enc)" "Token:$YARND_TOKEN"

A recent spam feed prompted me to build some more admin endpoints that can be used to nuke feeds out of a pod’s cache. My pod’s anonymous/discover views looks quite nice and meaningful now 👌

@slashdot@feeds.twtxt.net No shit 💩

The fact is, right now I don’t find LLM(s) very useful, more of a waste of time and energy. But as you say, they’re here to say, we’re continuing to “evolve” the tech, so let’s see what happens…

@bender@twtxt.net That’s true 🤣

@darren@twtxt.net Hey! 👋 You still use this pod? 🤔

@bender@twtxt.net All I can say is doing a Google search for Cost of a running an LLM is rather interesting…

@bender@twtxt.net

There has been other things/technologies/stuff that worked/performed/functioned bad in their infancy, but then get better, and more useful, over time.

Curious if you can name and describe an example or two? I’m struggling myself to think of one, but I’m sure there are examples and we’re just being unreasonably harsh 😅

@xuu Yeah I think a @ in nicks breaks in general right?

I really can’t bring myself to donate to a school fundraising that makes $25m per year in revenue 🧐

@bender@twtxt.net I mean @movq@www.uninformativ.de is basisally spot on! These pieces of crap are just large expensive statistical models that occasionally spit out something sort of valid for some reason, but otherwise are the most useless idiotic and inefficient things I’ve ever seen or used.

I couldn’t agree more! Especially on the insane energy requirements of this “AI” garbage! 🤦‍♂️ It’s arguably worse than the cryptocurrency hype. It all needs to stop.