Bookmarked Disinformation and its effects on social capital networks (Google Doc) by Dave Troy

This document by US journalist Dave Troy positions resistance against disinformation not as a matter of factchecking and technology but as one of reshaping social capital and cultural network topologies. I plan to read this, especially the premises part looks interesting. Some upfront associations are with Valdis Krebs’ work on the US democratic / conservative party divide where he visualised it based on cultural artefacts, i.e. books people bought (2003-2008), to show spheres and overlaps, and with the Finnish work on increasing civic skills which to me seems a mix of critical crap detection skills woven into a social/societal framework. Networks around a belief or a piece of disinformation for me also point back to what I mentioned earlier about generated (and thus fake) texts, how attempts to detect such fakes usually center on the artefact not on the richer tapestry of information connections (last 2 bullet points and final paragraph) around it (I called it provenance and entanglement as indicators of authenticity recently, entanglement being the multiple ways it is part of a wider network fabric). And there’s the more general notion of Connectivism where learning and knowledge are situated in networks too.

The related problems of disinformation, misinformation, and radicalization have been popularly misunderstood as technology or fact-checking problems, but this ignores the mechanism of action, which is the reconfiguration of social capital. By recasting these problems as one problem rooted in the reconfiguration of social capital and network topology, we can consider solutions that might maximize public health and favor democracy over fascism …

Dave Troy

Bookmarked In Norway, the Electric Vehicle Future Has Already Arrived (by Jack Ewing)

De verregaande elektrificatie van auto’s in Noorwegen heeft een paar interessante effecten. De luchtkwaliteit in Oslo is sterk verbeterd. Stikstof emissie is ‘bijna opgelost’ in die stad. Niet alleen omdat er zo veel elektrische auto’s rondrijden, maar ook omdat aannemers bouwmachines verregaand hebben geëlektrificeerd. Ook dat beperkt de stikstof uitstoot verder. Zonder problemen met een overbelast elektriciteitsnetwerk ook.

Dat komt niet uit de lucht vallen. In 2013 sprak ik een Noorse jurist op een conferentie in Ljubljana die me toen verbaasde door me te vertellen dat elektrische auto’s in Noorwegen al de meest verkochte nieuwe auto’s waren. Dus al meer dan een decennium worden er vooral EVs op de weg gebracht. De Noorse overheid begon al in de jaren 90 (!) met het stimuleren van elektrisch rijden d.m.v. subsidies en belastingvoordelen. Dat is zelfs nog ruim een decennium voor we hier een premier kregen die in 2013 visie als vies en hinderlijk woord publiek afschafte.

We are on the verge of solving the NOx problem

Tobias Wolf, Oslo’s chief engineer for air quality

Bookmarked The Expanding Dark Forest and Generative AI by Maggie Appleton

I very much enjoyed this talk that Maggie Appleton gave at Causal Islands in Toronto, Canada, 25-27 April 2023. It reminds me of the fun and insightful keynotes at Reboot conferences a long time ago, some of which shifted my perspectives longterm.

This talk is about the impact on how we will experience and use the web when generative algorithms create most of its content. Appleton explores the potential effects of that and the futures that might result. She puts human agency at the center when it comes to how to choose our path forward in experimenting and using ‘algogens’ on the web, and how to navigate an internet where nobody believes you’re human.

Appleton is a product designer with Ought, on products that use language models to augment and extend human (cognitive) capabilities. Ought makes Elicit, a tool that surfaces (and summarises) potentially useful papers for your research questions. I use Elicit every now and then, and really should use it more often.

An exploration of the problems and possible futures of flooding the web with generative AI content

Maggie Appleton

On the internet nobody knows you’re a dog.

Peter Steiner, 1993

It seems after years of trollbots and content farms, with generative algorithms we are more rapidly moving past the point where the basic assumption on the web still can be that an (anonymous) author is human until it becomes clear it’s otherwise. Improving our crap detection skills from now on means a different default:

On the internet nobody believes you’re human.

until proven otherwise.

I can now share an article directly from my feed reader to my Hypothes.is account, annotated with a few remarks.

One of the things I often do when feed reading is opening some articles up in the browser with the purpose of possibly saving them to Hypothes.is for (later) annotation. You know how it goes with open tabs in browsers, hundreds will be opened up and then neglected, until you give up and quite the entire session.

My annotation of things I read starts with saving the article to Hypothes.is, and provide a single annotation for the entire page that includes a web archive link to the article and a brief motivation or some first thoughts about why I think it is of interest to me. Later I may go through the article in more detail and add more annotations, which end up in my notes. (I also do this outside of Hypothes.is, saving an entire article directly to my notes in markdown, when I don’t want to read the article in browser.)

Until now this forces me to leave my feed reader to store an article in Hypothes.is. However, in my personal feed reader I have already the opportunity to post directly from there to my websites or to my personal notes collection in Obsidian.
Hypothes.is has an API, which much like how I post to my sites from my feed reader can make it possible to directly share to Hypothes.is from inside my feed reader. This way I can continue to read, while leaving breadcrumbs in Hypothes.is (which always also end up in the inbox of my notes).

The Hypothes.is API is documented and expects JSON payloads. To read public material through the API is possible for anyone, to post you need an API key that is connected to your account (find it when logged in).

I use JSON payloads to post from my feedreader (and from inside my notes) to this site, so I copied and adapted the script to talk to the Hypotes.is API.
The result is an extremely basic and barebones script that can do only a single thing: post a page wide annotation (so no highlights, no updates etc). For now this is enough as it is precisely my usual starting point for annotation.

The script expects to receive 4 things: a URL, the title of the article, an array of tags, and my remarks. That is sent to the Hypothes.is API. In response I will get the information about the annotation I just made (ID etc.) but I disregard any response.

To the webform I use in my feedreader I added an option to send the information to Hypothes.is, rather than my websites through MicroPub, or my local notes through the filesystem. That option is what ensures the little script gets called with the right variables.

It now looks like this:


In my feed reader I have the usual form I use to post replies and bookmarks, now with an additional radio button to select ‘H.’ for Hypothes.is


Submitting the form above gets it posted to my Hypothes.is account

I have installed AutoGPT and started playing with it. AutoGPT is a locally installed and run piece of software (in a terminal window) that you theoretically can set a result to achieve and then let run to achieve it. It’s experimental so it is good advice to actually follow its steps along and approve individual actions it suggests doing.
It interacts with different generative AI tools (through your own API keys) and can initiate different actions, including online searches as well as spawning new interactions with LLM’s like GPT4 and using the results in its ongoing process. It chains these prompts and interactions together to get to a result (‘prompt chaining’).

I had to tweak some of the script a little bit (it calls python and pip but it needs to call python3 and pip3 on my machine) but then it works.

Initially I have it set up with OpenAI’s API, as the online guide I found were using that. However in the settings file I noticed I can also choose to use other LLM’s like the publicly available models through Huggingface, as well as image generating AIs.

I first attempted to let it write scripts to interact with the hypothes.is API. It ended up in a loop about needing to read the API documentation but not finding it. At that time I did not yet provide my own interventions (such as supplying the link to the API documentation). When I did so later it couldn’t come up with next steps, or not ingesting the full API documentation (only the first few lines) which also led to empty next steps.

Then I tried a simpler thing: give me a list of all email addresses of the people in my company.
It did a google search for my company’s website, and then looked at it. The site is in Dutch which it didn’t notice, and it concluded there wasn’t a page listing our team. I then provided it with the link to the team’s page, and it did parse that correctly ending up with a list of email addresses saved to file, while also neatly summarising what we do and what our expertise is.
While this second experiment was successfully concluded, it did require my own intervention, and the set task was relatively simple (scrape something from this here webpage). This was of limited usefulness, although it did require less time than me doing it myself. It points to the need of having a pretty clear picture of what one wants to achieve and how to achieve it, so you can provide feedback and input at the right steps in the process.

As with other generative AI tools, doing the right prompting is key, and the burden of learning effective prompting lies with the human tool user, the tool itself does not provide any guidance in this.

I appreciate it’s an early effort, but I can’t reproduce the enthusiastic results others claim. My first estimation is that those claims I’ve seen are based on hypothetical things used as prompts and then being enthusiastic about the plausible outcomes. Whereas if you try an actual issue where you know the desired result it easily falls flat. Similar to how ChatGPT can provide plausible texts except when the prompter knows what good quality output looks like for a given prompt.

It is tempting to play with this thing nevertheless, because of its positioning as a personal tool, as potential step to what I dubbed narrow band digital personal assistants earlier. I will continue to explore, first by latching onto the APIs of more open models for generative AI than OpenAI’s.