Bookmarked The Two Definitions of Zettelkasten by Chris Aldrich

This is a great essay by Chris Aldrich for several reasons. Because it aims to address the absence in the current hypelet around recent personal knowledge management tools and note systems like Zettelkasten of the realisation that everything in this space has a deep rooted lineage. In response he writes about the history of commonplacing, using card collection for creative, academic or professional output. Because the essay itself is the result of the very practice it describes. In the past months I’ve been reading along with Chris’ annotations (the value of which led me to share more of my own annotations too), and reading his essay I can readily recognise things from that stream of raw material. The notes Chris made from those annotations in turn resulted in this essay. Seven thousands words in a half-day effort.

Note to self: I should create an overview for myself and here about my note taking practice through the years and their inspiration. Just to further illustrate the history Chris writes about.

Hopefully those in the space will look more closely at the well-worn cow paths of analog history in deciding how to pave our (digital) futures. [….] The hiding value proposition of the older methods can be contrasted with the incessant drumbeat of the value and productivity inherently “promised” by those describing [only] Niklas Luhmann’s system.

Chris Aldrich

Favorited Yes! My IndieBlocks plugin is now up on WP.org by Jan Boddez

Oh, nice! Jan has been working on his own WordPress plugins w.r.t. IndieWeb for some time and now released some of that work as a public plugin. Current IndieWeb set-ups do not support the Gutenberg editor in WordPress as blocks are not supported. Jan’s plugin is created for blocks. Will need to try this out (also because my recent presentation at WordCamp on making WP IndieWeb compatible by default played a small role). Nice timing Jan, releasing it just so it can dominate my weekend 😀

Current version offers a single “Context” block, and, optionally, (1) some custom post types, and (2) the ability to add microformats2 to block-based (!) themes. More is on the way.

Jan Boddez

Also on IndieWeb News

In reply to What happens to my digital identity when I die? by Wouter Groeneveld

Ha, neat idea for a digital preservation strategy. Getting an ISBN number isn’t very expensive, 106 EUro for 1 or 28 Euro if you buy ten. With one, curation is key. With 10 it’s easy to do uncurated volumes in chronological order. Then do vanity press printing runs, to get the 2 copies of each to send to the Royal Library to save for posterity. Sounds like fun. If you’d do volumes, you don’t have to worry about timing, except for the final posts after the last volume. Maybe a last posthumous publication. If it is to be one book only, then choosing the right moment becomes important all of a sudden.

Which gets me back to this website. My intentions are to someday publish its contents in the form of a book, which can also be stored at the KBR

Wouter Groeneveld

Thursday I visited the first day of the two day Netherlands WordCamp that, after a 6 year hiatus, took place again. Some observations:

  • The venue was fun, in the middle of Burgers Zoo in Arnhem. From the room where I presented you looked out over the enclosure where the giraffes and rhino’s were. The entrance to the venue was through the tropical jungle greenhouse, with unseen birds and other animals making lots of noises somewhere above in the foliage.
  • The atmosphere was excellent, very laid back as well as open and curious to engage in conversation
  • It was my first time at WordCamp and somewhere above a third of the participants were as well, meaning there was a good mix of new people and old hands. A mix that helps set the atmosphere and tone of an event.
  • Sustainability was a big theme. Multiple speakers explored how WP web developers can reduce the footprint of the sites they create. Heard several things (reduce the number of URLs WP exposes, find ways of limiting hits generated by crawlers and bots, reduce the size of various elements in your WP site etc.) that I can follow up on. Also made me think again about running a RSS-only, otherwise completely headless website. Though given another takeaway further down the list, that isn’t a good idea.
  • The organising team had also focused on sustainability, and I was happy they went the same route as is the custom at IndieWeb events: all catering was vegetarian. I also learned that all food that wasn’t used was donated, pre-arranged with the local foodbank.
  • It was fun to meet several people in person that I’ve known online for a long time, such as Roel Groeneveld and Gerard van Enk, and co-organisers Marcel and Remkus. Others I had met before, like Bert Boerland. Plus I met some new people.
  • I think my presentation was well received.
  • I was a bit the odd one out, as I am a non-professional blogger who is a WordPress user, not a developer. It was a WordCamp, by the WP community and ecosystem, so the audience was largely commercially oriented. Web agencies, SEO, UX design etc. I am also someone who has a longer history with WordPress than some others, having seen it start as a blogging tool.
  • The WordPress community is large and densely connected, I’m an outsider to it, although I know quite a few people who are part of it. So this wasn’t ‘my’ crowd, but the energy from people meeting in person again after several years was palpable.
  • When the opening speaker asked ‘who here still reads RSS’ and only 5 or so raised their hands, in line with his expectations, was surprising to say the least. People either ditched RSS when Google Reader went away in 2013, or if they were younger never started with RSS. How do people read at volume if not through feeds? Actually going to websites and newsletters is the answer apparently.
  • Only a few people had ever heard of IndieWeb, although there definitely were some.
  • One of the volunteers I chatted with never heard of BarCamp. Nor realised that the Camp in WordCamp speaks of its lineage. This is akin to how in 2021 the supposedly first Dutch BarCamp was going to take place.
  • Those last three things underline what E and I have been chatting about in the past months regularly. How it is needed to keep talking about, writing about and transfer to others these things, repeatedly that we think are ‘just normal’ and essential. For things to be used, and be useful, you can never assume that telling the world about it is ever done. Which brings me back to why I was at WordCamp in the first place, talking about IndieWeb.


My first encounter with WordPress, at BlogTalk 2006 in Vienna. Photo Matt Mullenweg, used with permission.

In the past weeks I’ve been playing at times in OpenAI’s GPT-3 playground. You give GPT-3 a prompt and then it will provide some generated text. You could use that as prompt again, or add something yourself and let GPT-3 continue.

This morning, I read Liam Porr’s 2020 posting about a GPT-3 generated blog he kept for a few weeks. (I think keeping it up longer and positioning it like a personal blog would mean certain detection as generated or inauthentic. Unlike when Porr did his experiment, GPT-3 is now available to many, and more people would also be suspicious of texts as potentially generated to begin with.)

For fun I prompted the GPT-3 playground with the title and first few lines of my last posting on my recent use of the Hypothes.is social annotation tool.

My post remade by GPT-3

Below is the result GPT-3 gave me. After pasting the block-quoted part from the original as prompt, it generated the grey coded part.

10 Thoughts After Making 100 Annotations in Hypothes.is

I’ve now added over 100 annotations using Hypothes.is (h.), almost all within the last month. This includes a few non-public ones. Two weeks ago I wrote down some early impressions, to which I’m now adding some additional observations.

1) 100 annotations (in a month) don’t seem like a lot to me, if h. is a regular tool in one’s browsing habit.

2) The act of annotation feels good, even empowering. It’s a way of taking control of the web, or at least of one’s web experience.

3) Annotations can be very short, even just a single word. This is both good (e.g. for quickly annotating a lot of text) and bad (e.g. when trying to make a more nuanced point).

4) The annotation interface could be improved. In particular, it would be nice to have an easy way to see all annotations on a page, without having to open each one individually.

5) Annotations can be a great way to start a conversation. I’ve had a few annotations that have generated discussion, which is gratifying.

6) Annotations can also be a great way to keep track of thoughts and ideas. I’ve found myself using h. as a kind of “digital scratchpad”, jotting down things that I want to remember or follow up on later.

7) The fact that annotations are public by default is both good and bad. On the one hand, it encourages people to be thoughtful and considerate in their annotations. On the other hand, it can be intimidating, and I’ve found myself self-censoring on occasion.

8) The fact that annotations are tied to a specific URL can be both good and bad. On the one hand, it ensures that annotations are always relevant to the context in which they were made. On the other hand, it can be frustrating when the context changes (e.g. an article is updated) and the annotation is no longer relevant.

9) The fact that annotations are stored centrally (on h.'s servers) is both good and bad. On the one hand, it makes it easy to access and share annotations. On the other hand, it raises privacy and security concerns.

10) Overall, I’m very happy with h. and find it to be a valuable tool. I’m looking forward to using it more in the future.

Some first reactions to that GPT-3 text

  • The title (10 things about…) and partly adding the first numbered element, created the expected 10 point list. It’s a common enough marketing/personal branding type format for GPT-3 to pick up on. (Why did I use it yesterday? Because I was too lazy to categorize my observations, so I just listed and numbered them as I wrote them.)
  • Ignoring obvious things like the repetitiveness of the text, after reading you’re left with feeling like you’ve read a bunch of words but you remain unsure if you read anything of substance. The text suggests there’s substance though, the first person perspective, mentioning specific aspects. Yet then doesn’t really follow up. It reads like marketing text, content farmed text. It mentions things but doesn’t answer questions, nor pose them. Not a surprise, but it does show how much empty stuff there’s already out there (on which GPT-3 was trained in the first place). I recognise it as low-info text but not necessarily as generated text.
  • No links! No links, other than sporadic internal links, is the default in the media, I know. Yet hyperlinks are the strands the Web is made of. It allows pointing to side paths of relevance, to the history and context of which the posting itself is a result, the conversation it is intended to be part of and situated in. Its absence, the pretense that the artefact is a stand alone and self contained thing, is a tell. It’s also a weakness in other online texts, or any text, as books and journals can be filled with links in the shape of footnotes, references and mentions in the text itself)
  • No proof of work (to borrow a term) other than that the words have been written is conveyed by the text. No world behind the text, of which the text is a resulting expression. No examples that suggest or proof the author tried things out, looked things up. Compare that to the actual posting that in point 1 talks about social connections around the topic, links to other h. user profiles as data points for comparison, and elsewhere points to examples of behaviour, lists of h. users found created and shared, references other tools (Zotero, Obsidian) and larger scope (PKM workflows) outside the topic at hand, and experimental changes in the site it is published on itself. That all tells of some exploration, of which the posting is the annotation. This also goes back to my earlier remark of using a 10 point list as laziness in the face of categorising things as I’ve done in other posts (see what I did there? No links, cause lazy).

I think that’s the biggest thing that I take from this: any text should at least hint at the rich tapestry of things it is resulting from, if not directly discuss it or link to it. A tapestry not just made from other texts, but other actions taken (things created, data collected, tools made or adapted), and people (whose thoughts you build on, whose behaviour you observe and adopt, who you interact with outside of the given text). Whether it’s been GPT-3 generated or not, that holds.

Here are some impressions of my increased usage of Hypothes.is, a social annotation tool, in the past few days.
I follow Chris Aldrich his Hypothes.is RSS feed, and his usage has been both a good example and source of learning in the past months, as well as a nudge to experiment and adopt Hypothes.is myself.

What follows is a list of some early impressions that I formulated earlier today in an email. I thought I might as well post them here.

  • I played with the API to get a grip of how I might interact with the annotations I make, and with those of others I’m interested in. Added the existence of annotations to my blogposts in WordPress through the API too.
  • The Obsidian plugin to get annotations into my notes is an absolute prerequisite, because I need those notes in my own workflow.
  • I find working in browser for annotations somewhat distracting and uncomfortable (and I need to remind myself that they will end up in my notes, I feel the urge to also download it directly to my notes.)
  • I try to add an Archive link to the annotated article as the first link. It is slowly becoming habitual.
  • I mention existing notes in my annotations when I make them in Obsidian. Because it is one context that is a matter of starting a link [[ and I have forward search through all note titles. In hypothes.is being browser based this is a bit harder, as it means switching tools to retrieve the correct note titles. They do then work when they end up in Obsidian of course. At the same time, in my earlier use of a markdown downloader I would just mention those associations in the motivation to save a link, which is worse. Hypothes.is sits in the middle of saving a bookmark with motivation and annotating in Obsidian itself.
  • I do have some performative urges when annotating publicly. Maybe they will disappear over time.
  • The firefox hypothes.is bookmarklet I use doesn’t seem to play nice with archive.org. There’s another I haven’t tested yet.
  • I notice that any public annotations are licensed CC0 (public domain). Not sure what I think about that yet. It’s a logical step as such, but I don’t fully see yet what it may mean for subseqeunt learning processes internally and further down the process of creating insights or outputs. Is CC0 also applied to closed groups (educational settings e.g.)? Private annotations are just that, and don’t have CC0, but then you miss out on the social aspects of annotation.
  • My thoughts keep wandering to interacting with hypothes.is without using it directly to annotate webarticles through the browser. Are there any tools or people who build on or share with hypothes.is using the W3C standards / API, but don’t necessarily use hypothes.is themselves? Or run their own instance, which should be possible? I suspect that would open opportunities for a more liquid experience between this blog, my notes, and annotated articles.