tombarys

+ let LLM generate just scaffolds, skeletons + do not let it generate code (let it generate leading questions instead of answers) + let it test you (try learning-opportunities repo from CatHicks)

I just published my interview with Benjamin Riley at Cognitive Resonance. I enjoyed it a lot.

He is the founder of a consultancy that helps people understand how generative AI works — they use cognitive science and see AI as a tool that has strengths and limitations. There is a sad irony that Ben's father stopped taking his cancer medications after exchanges with chatGPT – and died shortly afterward. (you cam read the devastating story on Benjamin's blog or in a big NYT feature published recently)

We talked about some aspects of LLM use, AI hype, coding, kids and thinking and art in general.

Enjoy and sorry for my English, it is human made.

[Here is an alternative link if the "friend-link" above does not work: https://medium.com/@tombarys/we-need-the-friction-of-existen...]

Thank you for your feedback and the insight, .... you are probably right. Short live demo would be probably much better, I will think about it in the near term.

:D "massively multiplayer online dotolist" – sounds scary, but the usage chart grows steadily during the last days, so I will first involve my friend with senior experience (a person, NOT AI agent) to check and possibly prepare the backend and infrastructure.

Todo-list apps are nothing new. You might think sharing a handful of editable tasks among a few people would be dead simple.

You'd be wrong.

To my knowledge, no simple tool of this kind exists. There are countless complex apps that want something from you and your collaborators — a subscription fee, registration, an email address, your smartphone's private data, permission to send you notifications, and everything in between.

So I built something my elderly father, wife, kids, and less tech-savvy co-workers can use instantly, without explanation from their phones.

The solution is deliberately minimal: just a URL per collaborator, opened in their browser (desktop or mobile) — no new tools, no new habits. The list is the single source of truth; ongoing communication happens through whatever channels they already use: chat, Messenger, email…

I built https://dotolist.eu for myself as a proof of concept — but friends quickly adopted it, and you're welcome to use it for free. It is NOT vibe-coded. It is love-coded in Clojure.

Let me know if you find it useful. :)

it is simply about the fact there is a lot of lifestyle guidelines to walk as much as possible with “50 metres” textual context, but there is barely same amount of texts suggesting taking your car to a carwash with you as this is boringly obvious

> "Images can blend in the background, reading takes active processing so we're much more sensitive. And for the end user of a product, they care 0 or next to 0 about AI code."

Very interesting point!

Agree 100%.

I understand. The question is what does it mean to "survive" for someone.

For me survival means: - continuing to do my best at the language level – even if more people would start be gradually satisfied with less - I just believe that education, critical thinking and evidence-based principles are at core of humanity progress and one day it will make comeback - I am ok with smaller income and not wishing to exchange it for creating bullshit

The adaptation for me means: - generally: stay open-minded - I have to understand and somehow accept that the prospect is a bit grim but not to fall into some extreme and doom thinking - I have to explore new ways how to augment human-oriented creativity (with or without these tools)

What do you think?

This is a topic for another article! We tried hard to use (test) translation tools in some real-life scenarios. The results seemed like they can help first but then we spent a lot of time again to reach our standards. As a side-effect, our translators and editors felt they are losing their own creativity and sensitivity in that process.

We are a publisher which succeeded due to the highest-quality translations. Our readers appreciated it and ask for it. Czech language is very rich and these machines are not able to make the most of it. The non-fiction sphere needs a lot of fact-checking e.g. in local and field terminology too. So even we can imagine the process of translation could be technically shortened by machine translation, it would probably ruin our reputation in a long term.

At least for now...

You are right. It plateaued and even degraded in some way. Or we just got more sensitive to its bullshiting?

Good point! Thanks.

I like the perspective of "choices" during creation. It is an essential principle of the real art that it is a result of thousands/millions of deliberate choices. This is what we admire on the art. If you use mostly machine (or other kind of ways that decide instead and for you) for creation, you as an creator simply do less choices.

In this case, you delegate many of your experienced/crazy/hard decisions to the model (which is based on such decision made already by other artists but combines them in a random way). It is like decompressing JPG – some things are just hallucinated by machine.

From the perspective of pure human creativity, the result is thin, diluted. Even it seems like deliberate. In my opinion art lovers will seek for the dense art made by human, maybe asking even more for some kind of "proof" of the human-based process. What do you think?

> "Consumers don't care if art is generated by AI or humans"

Maybe not yet. The real "art" consumers were always very sensitive and asking for originality (thus scarcity). It is an essential principle of the art that it is a result of thousands/millions of deliberate choices. If you use machine for creation, you less choices. You delegate most of your talented/crazy/hard choices to the model (which is based on such choices of already talented but combines them in a random way). The result is thin, diluted even it seems like deliberate. In my opinion the most art lovers will continue to seek for the dense art made by human, asking for some kind of proof. :) The real art will be even more appreciated. I guess.

I am a book publisher & I love technology. It can empower people. I have been using LLM chatbots since they became widely available. I regularly test machine translation at our publishing house in collaboration with our translators. I have just completed two courses in artificial intelligence and machine learning at my alma mater, Masaryk University, and I am training my own experimental models (for predicting bestsellers :). I consider machine learning to be a remarkable invention and catalyst for progress. Despite all this, I have my doubts.

Thank you very much. I will think of a way to improve the shading while keeping the basic principle and simplicity. Thanks for the other ideas; it is still in progress. I added pasting the calendar from Apple Calendar yesterday.

Done

Actually, the spiral is ugly when it does not start at 8 a.m. ;) I added 6 a.m. and 7 a.m. as these were the most frequent workday start times users asked for. But I can also add other times for early birds.

For night owls: you can add an extra event (e.g., "11-11:01am Morning") and put all to-dos below this so they will start after.

I will think about possibilites.

Oh, thank you! You have many great ideas, @purple-leafy. This public version stems from the Roam environment where the outliner solves many things for you. Here I am using just a simple edit window without additional functionalities now.

Thank you for your time and expertise. I will look into them and answer (or ask) here, later.

Thanks, good idea, I will look into this!

Hey hackers! I've got something exciting to share: Nautilus Omnibus. It's not your typical time-blocking tool. The public prototype offers a unique circular day view that automatically advances all unfinished tasks. I initially developed this as a personal project (in Roam Research) and saw significant improvements in my productivity over several months. I then decided to share it with the world as a plugin for Roam.

Later, I shared some thoughts about Nautilus in an article (https://lifehacky.net/how-i-learned-to-plan-better-and-what-...), and many users expressed the need for a more accessible version of the tool.

As I am not a programmer (but a book publisher), it took some time... :) However, now everyone can try it regardless of their preferred platform.

Time-blocking is about dedicating blocks of time to focused work and other activities, balancing various aspects of life, and reducing the stress of an overflowing to-do list. In my experience, this approach can help precisely with this: it keeps track of what I can and cannot finish during the day.

I would love for you to try it out and share your feedback. Your insights are invaluable and will help improve Nautilus further. Check it out here; it is free and runs only in the browser (your data are not transferred):

https://nautilus-omnibus.web.app

I'm looking forward to hearing your thoughts!

I haven’t! I will check it, thanks.

More ob Nautilus here: https://lifehacky.net/how-i-learned-to-plan-better-and-what-...

Dear hackers, do to-do lists help you plan your day? Or do they increase your stress as they do for me? I’ve tried millions of apps, but their tasks always look one like the other — one task, one line. To-do lists are just unintuitive and useless for getting the bigger picture.

I tried to solve this using time-blocking in a calendar, but it did not work.

Finally, I experimented with a time-blocking concept that actually solved everything that I missed in to-do/calendar apps.

What do you think about Nautilus? Thank you for your opinion!

Even this is not answer to your question (others did it well), I love this hack for simple moving windows by clicking anywhere: https://mmazzarolo.com/blog/2022-04-16-drag-window-by-clicki...

My solution: I am a book publisher (age 50, 25 years in publishing). But during my life I found that I deeply love programming too in a way you mentioned – solving problems. Small, private conundrums. Sometimes creating simple apps. But just as a hobby!

If I had to make money by coding, this all would be gone.

So: do another job and code for fun. :)

Hi, I think it is perfectly natural – as others write here :) But still, you can do a lot about this. I am 50 and I feel even better than in my forties. We have three kids, I run demanding business (book publishing in small country) and I have many other responsibilities.

My way to improving has been pretty long (10 years of trying) but ... TLDR: I started to be more physically active, including strength training, completely overhauled my circadian – sleep habits (I sleep 10x better than years before). I suggest to follow Peter Attia and read books from David Sinclair, Satchin Panda, Matthew Walker... It pays off. :) Keep going, you can improve your mental abilities again.

PS: Last year I started to learn Clojure (I am not programmer, I just love it as I feel like functional languages are like poetry:). Yes, it is not easy, but I hope my first simple and useful app will be out and public this year. Just for fun.

I agree. It can be that "simple". My experience during/after lockdowns.

I think working from home can add too. Losing physical contacts during lockodown detached me from my work I love – which has shown clear after I started seeing our team again.

Suggestion: read Four Thousands Weeks from Oliver Burkeman;)

+ I suggest books from Shane Parrish – The Great Mental Models, which are exactly about solving all or at least many problems by using several (80-90) mental models.

Hi, I am the author of the mentioned article. It is not an ad :). In fact, I am Czech publisher of Matthew Walker's book "Why We Sleep" (mentioned in the article) and a bit lifehacker too – blogging in Czech-only until recently. I just wanted to check if my suspictions about the most hyped sleep-trackers are legit but waited for something better to compare them with. I believe Dreem can be used for this task, but, sure, it is not perfect – some people report worse EEG signal quality and thus less effective stimulations. Dreem removed weekly reports in last app update and there is nothing like Oura Cloud for "data mining" in Dreem, which is really a miss! I finally bought another Dreem2 for my mother, so I have to translate everything from English to Czech for her but I want to try to help her with her terrible sleep habits. The article will probably continue one day with my longitudial results (tested on me and her too). Ask whatever you want, I will try to answer. Best, Tomáš