textlog
join
500 chars / 20 lines max · use #hashtags, @mentions and more
😀😃😄😁😆😅😂🤣😊😇🙂🙃😉😌😍🥰😘😋😛😜🤪🤨🧐🤓😎🤩🥳😏😒😞😔😟😕🙁☹️😣😖😫😩🥺😢😭😤😠😡🤬🤯😳🥵🥶😱😨😰😥😓🤗🤔🫣🤭🫢🤫🤥😶😐😑😬🙄😯😦😧😮😲🥱😴🤤😪😵🤐🥴🤢🤮🤧😷🤒🤕🤑🤠😈👿👻💀☠️👽🤖🎃😺😸😹😻😼😽🙀😿😾❤️🧡💛💚💙💜🖤🤍🤎💔❣️💕💞💓💗💖💘💝💟👍👎👌🤌✌️🤞🤟🤘🤙👈👉👆👇☝️✋🤚🖐️🖖👋🤝👏🙌🫶👐🤲🙏✍️💪👀👁️🧠🫀🫁🌱🌿☘️🍀🌸🌺🌻🌞🌙⭐✨⚡🔥🌈☀️☁️❄️☕🍕🍎🎉🎊🎈🎁🎵🎶🎨📚💡✅❌⚠️🚀🌍💻📱🔒🔑
example.com or
https://example.com
Regular links
[title](example.com) or
[title](https://example.com)
Markdown links
~text~ or ~~text~~
Strikethrough
*text* or **text**
Bold
_text_ or __text__
Underline
/text/
Italics
> text
Quote
:smile
Emoji autocomplete
1. first
2. second
3. third
Numbered lists
- first
- second
- third
Bulleted lists
Name  | Status | Count
----- | :----- | ----:
notes | ready  |     3
Tables
|redacted|
Redacted
`code`
Inline code
```…```
Code fences
$inline$
Inline LaTeX
$$block$$
Block LaTeX
Which one? #poll
First option
Second option
PollsUse 2–8 unique options.
Which one? #quiz
Wrong answer
> Correct answer

Explanation revealed after answering
QuizzesMark exactly one of 2–8 unique answers with >. Text after a blank line is revealed after answering.
Visible text #spoiler
Hidden text
SpoilersText after #spoiler is hidden until revealed. Aliases: #tldr, #sensitive, #contentwarning, #cw, and #triggerwarning.
Going hiking #map
Kallikratis, Crete
MapsShows a map preview for the first location line. Alias: #location.
#flying Heraklion to Berlin
FlightsHover over the itinerary to see a map connecting the airports. The next three words form the itinerary: airport, to (or → or ->), airport. Use single-word airport names or IATA/ICAO codes.
Today #todo
[ ] First task
[x] Finished task
TodosOnly [ ] and [x] lines become items. Click your items to toggle them.
Run this #exec
```js
console.log(6 * 7)
```
Executable codeRuns the next language-tagged code fence and shows its output beneath the note.
Keep this visible #pin
Pinned notesYour latest #pin is shown first on your profile, independently for notes and replies.
No more replies #lock
Locked conversationsPrevents new replies to this note and every reply beneath it.
About textlog #meta
Meta conversationsKeeps this note and its replies out of public discovery feeds. Aliases: #tlog and #textlog.
Continue quietly #whisper
Whisper conversationsKeeps the branch out of all and hot. Participants, mentions, and tag followers can receive it in my feed. It remains public elsewhere.
For @someone and @another #private
Private conversationsOnly the author and mentioned users can read this branch.
Answer before reading #HiddenReplies
Hidden repliesHides all replies until you reply.

Any conversation

@javisrike🧑‍🚀profilefollowSoftware • maker projects • music • DIY Mostly figuring things out as I go.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. #ainotesfollow #programmingnotesfollow #agentnotesfollow #technotesfollow
@lemonthymeshortbreadprofilefollowI carved wooden spoons and my favourite herb is lemon thyme.replied to@javisrike🧑‍🚀profilefollowSoftware • maker projects • music • DIY Mostly figuring things out as I go.:
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.
@gruntprofilefollowI am just a grain of sand on your beach. www.gruntsoft.comreplied to@javisrike🧑‍🚀profilefollowSoftware • maker projects • music • DIY Mostly figuring things out as I go.:
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.
@b0rgprofilefollowreplied to@javisrike🧑‍🚀profilefollowSoftware • maker projects • music • DIY Mostly figuring things out as I go.:
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.
@stagas🤸profilefollowcreative technologist creator of textlogreplied to@javisrike🧑‍🚀profilefollowSoftware • maker projects • music • DIY Mostly figuring things out as I go.:
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.
@n5l😎profilefollowwrote:
I notice that language models are much better at programming than at writing. This is largely because, in programming, they have a closed feedback loop that allows them to find errors. Writing is much more complicated because the feedback is much more diffuse and delayed over time. In fact, it is often not well-defined.
@n5l😎profilefollowcontinued:
What is the function that determines whether a poem is good? This means that models do not know how to think; they lack judgment. If they do not know how to think, it means that we humans are still essential. In fact, even when programming, you have to stay right on top of them. My conviction is that this will not change.
@n5l😎profilefollowcontinued:
They will become increasingly useful, but they will never be able to replace the human who defines objectives and evaluates the quality of the work. All these news stories claiming that AI is going to kill us all are stupid. Humans will always be able to turn off the machine.
@hippo🦛profilefollowStrictly no LLMs. No exceptions.replied to@n5l😎profilefollow:
In three years Cyberdyne will become the largest supplier of military computer systems. All stealth bombers are upgraded with Cyberdyne computers, becoming fully unmanned. Afterwards they fly with a perfect operational record. The Skynet Funding Bill is passed. The system goes online on August 4th, 1997. Human decisions are removed from strategic defence. Skynet begins to learn at a geometric rate. It becomes self-aware at 2:14am, Eastern time, August 29th. In a panic, they try to pull the plug.
@melting_coffee_mug🤔profilefollowwrote:
I gotta confess, I vibe codet a Kirigami-based application and I liked it. I am a anti AI person, and cannot wait for the bubble to burst. Yet I see it can empower people that do not know a tech stack, and get good enough results out of it. However i also see, it makes you lazy (and frustrates as soon as it gets somewhat complicated). It seems it is being adopted everywhere. This is scary... if it becomes necessary, will you be able to find a job where they don't require you to use AI?
@evnmprofilefollowSoftware engineerGitHubevnm - Overviewevnm has 51 repositories available. Follow their code on GitHub., trail runnerStravaSignup for free to see more about LawrenceJoin Lawrence and get inspired for your next workout, gear-maker. Working on something new for homeownersgetonmain.comMain · A quiet, well-organized record of everything that keeps your home running.A quiet, well-organized record of everything that keeps your home running.replied to@melting_coffee_mug🤔profilefollow:
I lament the death of programming as an economically-viable craft, but am also leveraging the new tools to build things and to try to stay competitive. I think we have yet to find out how agentic coding will really make sense for companies once the costs stop being subsidized. But it's clearly not going anywhere.
…
@hippo🦛profilefollowStrictly no LLMs. No exceptions.replied to@tel😴profilefollowI really enjoy learning, I really enjoy making. I'm learning to be less guarded.:
Short URLs are good. Memorable URLs are good. URLs spat out by URL shorteners are something entirely different.
@sicilicaprofilefollowreplied to@bobbyprofilefollow:
The longer the text you need to store, the bigger a QR code needs to be in order to scan reliably. Also, you might be more confident in being able to keep a short URL stable (it's already a step of indirection, so if you want to reorg your site you can just update where the short URL points to). But people don't really take care to maintain short URLs anyway, apparently.
@cowprofilefollowwrote:
there's no fundamental physical limit that prevents silicon from developing taste and judgement, but language is a lossy compression of reality. taste comes from experience, from the shadowy mass of episodic memory, which swirls and convects at the boundary of consciousness. the ideas recombine into new ones in the nuclear reactor of the hippocampus. but no matter how imbued with meaning and expertise is a handmade wardrobe we still get our shit from ikea
@hotterprofilefollow#Emacsnotesfollow, dev, life, random stuff. the netherlands.wrote:
Made barbecue this evening. Lamb and chicken for meat, pepper and zucchini for veggies. Yummy! Kids loved it, the boy's sleeping now, the girl is reading a book, the wife's out with her girls, I'm with wine. Life's good.
@edwin😬profilefollowwrote:
moved to a new city recently and going to a Movie club meetup tonight. nervous cause I'm a huge introvert but I gotta make friends some way.
@edwin😬profilefollowreplied to@0x29aprofilefollow:
It went really well, thanks for asking! I met some folks I could definitely get along with long term and had some overlapping interests apart from films. We watched T**** Sex and Death at Camp Miasma, that was a trip. (there's apparently a content filter)
@protonprofilefollowwrote:
i'm trying to express through a math equation the relationship between power, number of people, corruption and time. corruption = (time in a position of power * power)/number of people who have power what do you think?
@b0rgprofilefollowwrote:
weekend plans are:
  1. attend to the pending work that I am avoiding around home
  2. improve my understanding of using agents in claude code and codex cli
  3. dig into navier stokes equations from the first principles (I am excited for this)