any · textlog

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.

moreless

I read Still trying to figure out the boundaries of these tools' strengths without outsourcing important thinking, problem-solving, and the collective building-up of a mental model of the systems we're developing. The shape of LLM tools as tools—fit for a purpose, ergonomic—is becoming clearer, and human patterns of behavior with them that do more harm than good are also becoming easier to recognize.

sometimes my devices will make noises that seem to go off for no reason. it really stresses me out though, I can't help but always think something is doing it and if it's not me, then what?

what kind of noises? drives spinning up/fans ramping up?

random beeps and a sound that seems like the notification but it just isn't. I don't know maybe I'm crazy

Would a CO monitor help here? I mean to err on the side of caution etc.

I don't believe I know what that is

It was a reference to this nypost.com/…/i-thought-a-stalker-…was-even-scarier/

…

oh, I may not be able to get this since i am too young to purchase anything online and I lack the funds. I will definitely urge my family to get it though, because I do constantly have issues of hearing things or believing someone is watching me

Watched the Daily Show bit about AI this week, my wife found the interview with the whistleblower guy really depressing. That interview dramatically undersold that all the sketchy hacking shit that's happening right now is coming from 1 company.

Just trying to see how this works

Up earlier than I should be today. The witching hour got me. I started thinking about how many in society have decided they prefer screens and artificial words over real words and real connection. Have we collectively decided it’s easier to just not be vulnerable? I should go back to bed…

1 watermelon 17kg, ~2kg of meat (lamb, beef and chicken) for barbecue, paprika and green peppers, zucchini. Total 92 eur. Life’s expensive in 2026.

its true. but meat should be expensive imo

I was contemplating pwc372, p2 and came up with “- 1+&/-/'(&'(?x)=x)@0 -1” (goal). Conceptually I like it, but maybe it can be simplified further?

I have to constantly be working or I get very agitated. Is this ? I don’t like entertainment other than background music while working and maybe before going to sleep I watch a series on Netflix to relax. That’s when I’m on my introvert mode. When I’m extrovert (I’m ambivert) I have to constantly be around people and outdoors, I get agitated indoors, can’t work at all and definitely can’t watch anything. How do these two personalities co-exist in me?

anyone else seriously into agentic loop development?

I've been working with physical AI - Letting LLMs control robots in a warehouse to collaborate and collectively come up with a physically correct solution to carry out a natural language intent. We had to study the reactive nature of agents, nudges they required, etc.

that's awesome and near my heart. I kicked off a personal project emergingrobotics.ai

haha that's a coincidence. Site looks awesome. The moving away from ROS2 part is so true. One of our main potential customers for physical AI solutions (a telecom provider in JP) communicated the need for agents to be able to pick up controls from any vendor

…

I apologize if that sounded obvious/non-obvious/amateurish haha. I was an intern and worked more on the agentic side of things, it was just a non-primary experiment

Last weeks post about "if you're not using an LLM router, how do you know wtf is going on" inspired me to spin up a couple of OSS options this week and wow were they right.

what did you find?

Well, I know conceptually what is passed between my client/harness and the model provider, but to actually see it is mind expanding.

i got into the fashion to vibevode some utility apps for myself. i didn't review the code. they work fine. colleagues are interested. i don't feel comfortable to put such stuff on $Github. have no good consciousness with unreviewed and likely ununderstood (stack I am not really familiar with). internet is full of people who don't care, I know. i tend to overthink. what about you?

i think over time people might care less and less.

everyone! it’s time ☕

Morning from Tasmania time for me

Very satisfying taking something that underperforms and slowly pushing it to 60 fps.

Probably because it's very frustrating to be below that.

testing, testing. is this on? hello?

hello! welcome!

WeakNotes 2026-10-29

A thing I've been doing lately is trying to come to the same conclusions others have without looking their the direct techniques and code. Last night I tried to figure out why people do vector based retrieval for RAG and ended up running these experiments: n0tls.com/…/2026-09-03-i-think-…rag-with-grep.html I'm still going to do an explore agent.

Here's a follow up from last night: n0tls.com/…/2026-09-05-fine-tuning-…tiny-retriever.html This has been a great way for me to learn in this space. Learning with AI has been such a fun time for me.

created a poll:

What do you think is better?

Students stay in the same classroom all day, teachers come and go60%

Teachers stay in the same classroom all day, students come and go40%

Nobody stays in the same room all day, rooms are booked for the duration of the lecture period0%

5 voted

I picked the first, because you didn’t specified level, and I assumed below college.

hello hello

hello!

Greetings.