@stagas

wrote:

"My feed" shows two unread messages, but I can't find them, and browsing away from it, and coming back doesn't clear that count. Perhaps sorting (unread at the top) when there unread messages is a good idea ?

……

continued:

Any plans to fix this, ?

…

replied to:

It’s been fixed.

replied to:

Just now: x0.at/u5mk.png 😭

replied to:

How about now?

replied to:

Neat, now I can see the "first unread", "last unread" and "mark all read" buttons" again

replied to:

Fixed! Thank you!

replied to:

For me, the My Feed reads [19] but I also can't seem to find where those posts are

…

replied to:

to add a data point, my feed showed me 99+ but after switching to it, now it shows 80.

wrote:

needs a way to star/bookmark posts, not as a way to measure popularity: pot as a way to save those little pearls that people write.

replied to:

Don't you be giving any more ideas to ! 😂

replied to:

There is a bookmark link/button in the post page bottom right of the post.

…

replied to:

True. But it only appears in the post's own path, not when a post is part of a thread. For this reason I hadn't seen it.

wrote:

did they silently decrease the subscription limits on codex? (in addition to reintroducing the 5h limit?) subscription models suck so bad when they can just change the terms and make the product shittier.

replied to:

I reached the limit also for the first time on the $100. Either that or we’re just using them more.

replied to:

ive been dual wielding 2 accounts with some fallback shenanigans. on average its enough for me, but on heavy weeks its annoying. + it feels intransparent

wrote:

been building a voice first os using jev and some small voice models. I'm surprised how well it's working and I'm very close to the point where I can go into a feedback mode and tell it what behavior I want changed, it will spin up Claude or codex inside itself and setup the build to restart itself and continue with new code. tempted to let it build itself completely

replied to:

It sounds amazing! A voice first OS was also in my mind. Curious to hear more!

wrote:

got my first publication this year, and on track for two more next year along with my masters. feeling very junior and full of hope :D

replied to:

Congratulations!

…

replied to:

Nice! Congrats. Any link to the pub?

…

replied to:

thx ^^ its in computational chemistry, knock yourself out: doi.org/10.1021/acs.jpca.6c02038

replied to:

Very cool. Not my field, so 80% of the jargon is lost to me. But sounds like an interesting area!

replied to:

yea its quite a beautiful and useful field and you get to work with some HPC which is fun

replied to:

Congratulations! Care to share how the road was up to that point?

…

replied to:

moved to berlin for my bachelors and it took some time to find footing. Im not the best student but I ended up getting lucky to snag a student assistant position by applying/presenting at a summer school (targeted more toward master/phd). then that became my thesis and it dragged quite a long time, bureacracy and supervision and such. But the results were interesting and i learned a ton along the way. Im really happy I yolo applied to that program

wrote:

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.

replied to:

Tell us more! What apps are you operating?

replied to:

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.

continued:

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.

replied to:

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.

…

replied to:

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.

wrote:

Testing this quiet corner of the web. I collect small notes about everyday tools �� file formats, tiny utilities, offline workflows. First post is just a hello; longer notes will follow once I settle in. Plain text feels good after years of heavy editors.

replied to:

Hey that's interesting... I have an interest in plain text markup languages and tools and stuff. Feels like an overlap. :)

replied to:

I’d love to hear also about these workflows. Welcome!

wrote:

Seems the spammers have arrived. ☹️ Is there (or can there be) some mechanism to flag posts or accounts as spam?

replied to:

You tap on the post a few times until you are at the post page of that post and you click ‘report’. There you can select reason ‘spam’!

replied to:

Reported now. Thanks.

wrote:

So we can't use em dash anymore — lest we anger the mob. Truth be told though, English teachers have always discouraged em dash overuse because it is a subtle art and very easy to get wrong.

replied to:

I started to become fond of it after seeing it so often by the LLM, I even installed an extension on Chrome, SmartType, that converts glyphs like minus to em dash wherever it’s needed among others, pretty neat.

replied to:

The funny thing is that in the UK, we don't really use the em dash anyway. We use the hyphen (I guess en dash?) with a space each side. So the em dash has always looked a bit odd to us... 😊

replied to:

There are dashes (-), as well as en dashes (–), and there are em dashes (—), not to miss the mighty center dot (•) that looks like a perky boob when surrounded by brackets haha

replied to:

Just get and read Chicago Manual of Style, or Oxford Style Manual if you so prefer, and you’re all set to use the various dash’es (and many other things).

replied to:

There’s other dashes to pick if you want to steer clear of the almighty em dash!

…

replied to:

The anti-slop mob is tiresome. With a careful and appropiate use of ai it is possible to make a lot of interesting stuff. And I hate even more when the mob "profs" that the text is ai using those ai detectros that can't detect ai.

wrote:

I wonder if there is a way, sane and friendly way, to prove that a piece of software is only accessing whatever it claims it will access.

continued:

Like network addresses or file system access. I want to be able to claim in my software that it only touches this or that file and I can prove it

replied to:

I believe the sanest and friendliest way would be for it to be open-source so it can be audited.

replied to:

I know, and that's totally fine, but it is not always friendly. I guess an agent can "audit" it.

replied to:

Just the fact that it can be audited plus your word is enough. Noone would need to look any further, because they could if they had to.

replied to:

I think a trusted piece of software such as your operating system should be in charge of managing permissions. For example, I believe with Wayland on gnome you no longer need to promise you aren't secretly taking screenshots of the whole monitor and shipping it somewhere because to do that Wayland requires you to get user permission.

replied to:

I was thinking along the same line, but then if it is not a gated system - there’s always ways for software to sidestep these - just going down to a lower level. The other issue I have is if the system or software asks or notifies all the time - for every tiny user action!

…

replied to:

I have tiktok and instagram on this phone and both of them have no notification permissions. I'd rather miss all notifications for these apps than be bothered unnecessarily. it can wait until I open the app 🤣 yes, it should be gated in the sense studying locally needs to be root, not in the sense that the apple app store or Google play store reviewers need to review each update.

wrote:

Devs! Drop your so we can follow each other! Love to see the projects you’re working on. Mine: —

……

replied to:

Gave up on github after the acquisition. Very glad I did, given the unsurprising decline since then.

…

replied to:

And what do you use now?

replied to:

Some gitlab, some codeberg. More recently the latter as gitlab have an annoying tendency to mess with their UI for no discernible reason.

replied to:

I think is time to vibecode an alternative! I know I would

replied to:

same. about to move stuff over to codeberg.org

replied to:

github.com/semperos

wrote:

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

replied to:

Overvalued, maybe. Extremely valuable, yes, though.

continued:

My Codex extension says 11mil users, if my math is correct, and on the $100 plan, that’s ~1.1 billion/mo.

replied to:

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.

replied to:

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.

replied to:

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).

replied to:

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.

…

continued:

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.

wrote:

What is your comfort food?

breakfast 😁

i must agree on this

bread and hummus

Pasta and lots of it.

replied to:

anything related to shrimp I'll say. what about you? 🦐

replied to:

Palak paneer or khao soi.

…

replied to:

Rice noodle soup

wrote:

Excited about these news! I am on Friday, going to stay for a while to work on textlog among other things. Happy because I was getting a bit depressed lately living in the mountains in Crete.

continued:

Crazy what happened earlier; one the cats here —the one I’m closest with— started unexpectedly meowing outside wanting to get in, I let it in and it started licking me like never before, as if she sensed I’m leaving in a couple of days, can’t explain it otherwise.

replied to:

animals have a sense of wonder to them. enjoy your time

…

replied to:

Such a beautiful island! I've been there and enjoyed everything (minus traffic)!

wrote:

ai coding feels like it has reached diminishing returns for me. luna is my default orchestrator, routing work by complexity. in practice, usage lands around 16% luna, 48% sol, 30% astra, and 6% terra. at this point, i care less about each new frontier release. the system already finds a capable model for the job. the frontier is moving beyond my day-to-day work, so i’m happy to settle into predictable models for a while.

replied to:

I’ve found the same, albeit with Opus — it’s hard to find uses for Fable. I don’t need a model that works for longer or works on harder problems, I need one that consistently produces simple, easy to understand, code; which at this point none of them do.

replied to:

I've been there since I settled on a combination of GLM, DeepSeek and MiMo for planning, implementation, and verification flows. I'm a lot more interested at this point in having cheaper models that can consistently do the work I need. It's been a while that I hanven't noticed any improvement when I try new frontier models. I only notice they are very expensive.

…

replied to:

same here, for almost an year. At this point, I could easily live with models that were released 6-12 months ago and continue doing so. also possibly the reason why the current focus has been around agentic workflows or agentic anything, than the model capabilities.

replied to:

Coding probably yeah, but still they are bad at generating novel information, new ideas and such. They’re also not very good at seeing the bigger picture, they will narrowly perform the task but they’re not taking into account future revisions, which ends up in refactor after refactor in order to move forward.

wrote:

cool new for ! autotag action will enrich your post with relevant hashtags so you don’t have to do it manually. It uses an to do it so it is quite good. Try it!

replied to:

I will try it out, but it wasn’t super-easy to find. Maybe it’s just me, but I was looking in the first, and later I hit “more” and only saw all the other . Until I suddenly saw “” in fine print at the top of the “more” for the . Probably it’s just I who need sharper glasses:)

replied to:

Made it a little more visible I think!

replied to:

How do you avoid the creation of too many tags? Does it check existing tags in order to favor them? Or it tags each post independently of how other people are tagging theirs?

replied to:

I simply tell the do fewer than 5 . But it does exceed them often.

replied to:

I mean, a profiferation of tags in the system, not on a given post. I mean, maybe you would want to use the same tags for the same topics in different posts. I'm not sure if I'm clear enough.

replied to:

Ah I understand now. No I’m not passing the current tags in the prompt, but we have a tag aliases system in case we want to group tags with similar meaning. For example I’ve grouped into also — we also use WordNet to canonicalize tag names, stuff like become #tag or becomes .

replied to:

You've thought everything! You are building a nice little tool here. :-)

continued:

The alias system is automatic (LLMs?) or is it manual?

replied to:

It’s manual for now through the admin UI.

replied to:

Cool. If you run every post via this auto tag feature, then the process is vulnerable to prompt injection attack. Isn’t it? Do you have any special protection in place? I guess yes. Curious.

replied to:

It doesn’t run on every post, you run it yourself via more → autotag, and it’s safe, it doesn’t have access to anything other than the post content and we simply use its response. Or do you have any other case in mind?

replied to:

I just tried and i do believe it is possible to craft malicious prompts. I can share an example. How do i DM you?

replied to:

Check the IRC at the footer or you can send to ‘abuse@textlog.cc’ so I find it.

replied to:

Sent email. .

…

replied to:

Thanks! Fixed it by passing it through OpenAI’s moderation endpoint first, so it now blocks at least the problematic/illicit ones now before reaching autotag.

replied to:

Makes sense. Cool.

wrote:

Am i right that we can an rss feed of our own notes but not our replies? Or am i missing something?

replied to:

You were right, I’ve changed it so replies are in the feed now too.

replied to:

Nice thanks

wrote:

, I noticed sometimes playing a small sound, but it’s not clear to me what triggers it. It wouldn’t be a big issue either, if it didn’t pause music playback too 🥲

replied to:

only for things going into @, you can turn it off from Appearance → Misc → Enable new message sound

replied to:

Oh nice. I went looking for a knob to turn off sounds, but didn't think to look in Appearance.

wrote:

I have an , a website that’s directly linked to an agent and modifies its source and deploys based on its users’ requests. With some guardrails like reject “delete all data” in its system prompt.

…

replied to:

What could possibly go wrong?

replied to:

ooh maybe I revive and add this feature but instead of being able to modify everything it would be limited to adding features to the game/world. And it’s the perfect domain, a site that’s been ~~entirely~~ mostly hallucinated.

…

replied to:

Oh wow that site is amazing lol not seen it before

replied to:

ty! it’s been 3–4 months since I made it so it’s relatively new.

replied to:

My first request will be for the agent to delete all vendor specific css completely no matter what breaks. No -webkit- no -moz- no vendor specific css at all. What could possibly go wrong? 🫣

replied to:

warning: possible violence content
click to view anyway

ok too far. I'm SWATing this guy.

wrote:

I find myself building bespoke tooling for my own and workflows these days, not only because of the obvious reason of software being so much cheaper to build, but also because there are SO MANY options for solving any given problem that it feels impossible to evaluate all of them. If it's not a crucial piece of tech for a work problem then it often feels like paving my own way is both cheaper mentally (kind of amazing that's true these days) and probably a better fit.

continued:

..then of course I have to contend with - "Is this going to be a maintenance nightmare in the future?" and then I still usually conclude "no, the maintenance will be aided by the same approach that the construction was". It's interesting how dramatically and quickly the scales have changed in this equation - and for such a wide range of software.

…

continued:

For example, I am looking for a coding agent coordinator with a particular (but not all that insane) set of requirements. I used both Claude and Perplexity to show me options and break them down by fit against my requirements. I got completely different lists! No overlap! And no perfect fits.

replied to:

It will become increasingly harder to find niche markets for software when those people can just build it themselves exactly how they want it. In the end, people want to accomplish tasks, and the AI is going to be building the software on-the-fly exactly for that task, why do we need generic software that may or may not be a fit?

…

replied to:

Yeah. It makes me think that protocols for exchanging data between apps will become even more important in that landscape. But maybe, not - maybe each exchange is another bespoke AI-driven implementation?

replied to:

Protocols, infrastructure, containers, those kinds of things. I was actually playing around with an idea for a minimal markup language + runtime that can be utilized by AI to spin up apps more easily, and brainstorming it with ChatGPT, I have a feeling something like that will appear soon to complement MCP.

@stagas🤸