In my professional life on the web, I tend to visit lots of the same URLs frequently. While I have (most of) them bookmarked in my browser, I usually don’t navigate to the bookmark and click it.
I start typing in the URL field of my browser (Firefox) and since autosuggest also searches the bookmarks, those are often visible. I realized though that this is still often too slow and not straight forward enough: It happens that many URLs are very similar and have the same first part, such as on Github many repos are under the same organization.
So a while ago I started using Alfred’s snippets to expand URLs for me. By using / as a suffix1, this allows for speedy expansion of URLs I visit frequently. A bonus is that the same expansion works in other places where I need the URL, e.g. for linking it in blog posts.
So, for example, I have the snippet g/a/ to expand to https://github.com/akirk/. If I then continue typing fr, my browser can autocomplete much more precisely because I have already entered part of the URL to https://github.com/akirk/friends which I often visit.
Hope this can serve as an inspiration!
Although I natively speak German, I have switched to US (Intl for the inverted-L Enter key, I cannot let got of that one) keyboards a long time ago to benefit from dedicated keys for square and curly brackets, this also means I have a dedicated key for slash ↩︎
With the new Completions function calling API you can actually enable ChatGPT to access the internet. I did a few quick experiments where I provided it with a function called get_extracted_url_contents. See how it made use of it:
Prompt: Get some news from a random US news website on the internet. Fetching https://www.cnn.com by request of ChatGPT. AI (239 tokens used): According to CNN, the breaking news is that the former US president has been arraigned on 37 federal charges involving the alleged mishandling of highly classified military documents. This is a historic first.
Or from a German website:
Prompt: Get some news from a random German news website on the internet. Please only respond in English. Fetching https://www.spiegel.de/international by request of ChatGPT. AI (1363 tokens used): Here are some news headlines from SPIEGEL International:
“Ukraine’s President Calls on NATO to Set Clear ‘Red Lines’ for Russia” – Ukrainian President Volodymyr Zelensky has urged NATO to establish clear “red lines” to deter further aggression from Russia. Zelensky made these remarks during a visit to Brussels.
“German Cabinet Approves New COVID-19 Restrictions, Including Nationwide Vaccination Mandate” – The German government has approved new measures to combat the spread of COVID-19, including a nationwide vaccination mandate for certain groups of people. These measures come as Germany faces a surge in COVID-19 cases.
“Turkey Summons German Ambassador Over ‘AfD-Led’ Turkish Ship Inspection” – Turkey has summoned the German ambassador to protest against the inspection of a Turkish ship by a German frigate in the Mediterranean Sea. The inspection was led by a member of the far-right Alternative for Germany (AfD) party.
“European Court of Justice Rules Hungary’s NGO Law Violates EU Law” – The European Court of Justice has ruled that Hungary’s controversial law that restricts the activities of non-governmental organizations (NGOs) violates EU law. The law required NGOs that receive funding from abroad to register as “foreign-funded organizations.”
Please note that these are just a few selected headlines. For more information, you can visit the SPIEGEL International website.
One more try for a specific site:
Prompt: Get some news from ORF. Please only respond in English. Fetching https://orf.at/ by request of ChatGPT. AI (1286 tokens used): Here are some news headlines from ORF:
Document affair: Trump declares “not guilty”
Babler presents his new team
Johnson vs. Sunak: Insults keeping the British on edge
Slovenia wants to keep borders with Croatia open
WKStA secures data in the Chancellor’s Office
Alaba is about to reach the next milestone
Alpine climate in winter is significantly too mild
IAEA “very concerned” about fighting near Zaporizhia nuclear power plant
NATO hopes Ukrainian successes will force Moscow to negotiate
Please note that these are only the headlines and more details can be found on the ORF website.
$ php summarize-url.php https://alex.kirk.at/2023/02/02/what-is-matrix/ Fetching https://alex.kirk.at/2023/02/02/what-is-matrix/ by request of ChatGPT. AI (1340 tokens used): Matrix is an open-source internet-based chat system that operates on a federated model similar to email. It allows users to send and receive messages through homeservers, which maintain up-to-date copies of chat rooms. Matrix rooms can be either unencrypted and openly discoverable or end-to-end encrypted and invite-only, with encryption keys shared between users’ client software. There is a wide selection of Matrix clients available for different platforms, and a WordPress plugin called Chatrix has been developed to embed Matrix into WordPress posts or pages.
Here it required several runs to get the right response since it tried to access a lot of invalid URLs. But it eventually managed.
$ php research.php Prompt: Research on the internet who won the ATP French Open 2023 but don’t use a search engine. Fetching https://en.wikipedia.org/wiki/2023_French_Open by request of ChatGPT. AI (1085 tokens used): According to the information on the Wikipedia page for the 2023 French Open, Novak Djokovic won the ATP Men’s Singles championship.
Things also worked out in the end when I gave it the ability to do multipel requests:
$ php research.php Prompt: Research on wikipedia who won the (both men’s and women’s) ATP French Open 2023. If you cannot find a result, ask for a subsequent a function call. Fetching https://en.wikipedia.org/wiki/2023_French_Open_%E2%80%93_Men%27s_Singles by request of ChatGPT.PHP Warning: file_get_contents(https://en.wikipedia.org/wiki/2023_French_Open_%E2%80%93_Men%27s_Singles): Failed to open stream: HTTP request failed! HTTP/1.1 404 Not Found
Fetching https://en.wikipedia.org/wiki/2023_French_Open_%E2%80%93_Women%27s_Singles by request of ChatGPT.PHP Warning: file_get_contents(https://en.wikipedia.org/wiki/2023_French_Open_%E2%80%93_Women%27s_Singles): Failed to open stream: HTTP request failed! HTTP/1.1 404 Not Found Fetching https://en.wikipedia.org/wiki/2023_French_Open by request of ChatGPT. AI (1630 tokens used): The winner of the men’s singles ATP French Open 2023 is Novak Djokovic, and the winner of the women’s singles ATP French Open 2023 is Iga Świątek.
This has been just a quick exploration following OpenAI’s announcement. Curious how we’ll leverage this better in future!
For my personal use, I created a CLI ChatGPT client a few months ago. It has been very useful for me to have it available in the CLI quickly whenever I needed it (caveat, you need an API key!).
Unfortunately, for larger responses it can feel very slow, whereas the web version feels quite fast. But this is perceived speed because it shows you each word as it arrives and not just the whole response when finished (after all it is a completion AI that generates the response word by word).
So now, I have added streaming support to it. It now feels almost too fast :) The CLI has a few nice things such as readline support (i.e. you can go back to old queries with the up key) and it keeps all of your conversation in a text file. All of this in only 100 lines of PHP.
Matrix is an internet-based chat system like Slack or Microsoft Teams with a few key differences:
Open Source
It is open source (Apache License 2.0). Thus it includes the four freedoms (run it for any purpose, modify it, distribute it or a modified version).
Federated
There is no centrally controlled server, similar to e-mail (or ActivityPub): to send and receive e-mail, you need to have an account on a mail server. In Matrix, these servers are called homeservers.
When you send messages, these messages are first sent from your client (computer or phone) to the server, from the server to the recipients’ servers (in e-mail, you manually list them, in Matrix, these are all other people in the room), and then the messages are delivered to the individual participant’s clients. The benefit of this is that the client (like a mobile phone app) doesn’t need to be connected when the server receives the message and can catch up when it comes back online.
For this reason, Matrix account addresses look similar to e-mail (or Mastodon) addresses but they have the format @username:server.tld. Starting when a member of a homeserver joins a room, their homeserver will maintain a full, up-to-date copy of the chat room. Any message sent by others in the room will be sent to every participating homeserver. For this reason, joining a room can take a while because the server needs to (partially) populate its local copy from other homeservers. Because of the real-time nature of chat, the messages are exchanged very quickly between the homeservers as soon as that connection has been established.
A Matrix server can also be run in unfederated mode where it will not communicate with other servers on the internet, thus enabling a closed community. This decision can also be made on a room-by-room basis.
Encryption
Matrix rooms can be either unencrypted and openly discoverable, or end-to-end encrypted and invite-only. Because the server has no knowledge of contents or encryption keys, the latter need to be shared between the individual client software of a user. This is established through a verification step in which you use your other/old client to establish trust with the new one. Until this has happened, any encrypted communication is inaccessible.
For the above reason, there is a wide selection of clients for mobile and desktop, different operating systems, text based, etc. We have developed a WordPress plugin called Chatrix that allows embedding Matrix inside a WordPress post or page which allows something like we demonstrated in this GIF:
One thing that I like very much about my family is the anecdotes and stories. One thing that I am bad at, is reciting them.
So I had this idea to create something like a private Wikipedia for my family, where each person has their own page and family members can contribute to the stories, biographical data, and media.
Initially, I set up a MediaWiki, i.e. the same software that Wikipedia uses. It turns out, it’s not that easy to configure. The new Wiki editor is much better than directly editing wiki syntax but the complexity is high for a small project like that. Also, uploading media is quite a pain because of the importance of licensing metadata. In a private wiki, you’ll want the UI to get out of the way.
So, since I work with WordPress a lot, I had the idea to use WordPress for it. There are a number of wiki plugins for WordPress but they all seemed overly complex and not really geared towards a use case of users collaborating on creating a site.
WordPress has the advantage that you can set it up very quickly and got many options for setting it up. Plus, when you have already multiple blogs (e.g. for family members) on your domain, it’s easy to just add another blog to your WordPress multisite. The plugin works on a standalone blog, too.
Here are some screenshots that I made as a demo:
A homepage showing a missing wiki page.A person page with a missing wiki pageGutenberg view of a person page with the shortcodesA 404 page exposing the “Create Page” link in the headerA person page with external linksA calendar pageInserting a birthday calendar block
A big motivation for building the Friends Plugin is to be able to follow what my friends and family are up to. Probably the most important “follow technology” is good old RSS.
While mostly used for public posts, there are many examples of how it can deliver posts not meant for the public: the solution are individual RSS feeds per subscriber, for example paid podcasts, or like the Friends plugin gives specific feeds to friends that can contain private posts.
Now reality is that (no longer) every platform has RSS feeds. It’d be easier if they just provided themt but alas. There are plugins for the Friends plugin itself that make use of projects that have built custom parsers for specific services: Fraidyscrape and RSS Bridge.
Now unfortunately, a lot of friends and family post to Facebook or Instagram. It’s just impossible to follow these friends outside of the platforms.
They don’t provide (authenticated) RSS feeds. That would solve all of this.
They rate limit and quickly block IPs (especially Instagram) that try to read a few posts unauthenticated.
It’s unintuitive, developer centric and needs approval to get an API key, so it’s not something every user of the plugin can be asked.
Their HTML is scrambled with random class names, preventing any classic scraping.
So in the end, the content of my friends and family is locked in. It would be a solution for them to create their own blog (IndieWeb style) and share their content that way. But I am realistic enough to understand that the hurdles are great. They are already connected to their friends inside Facebook or Instagram. They get lots of likes and responses there. They are used to the UI and the apps. It’s just not good for anyone who doesn’t want to join the Facebook ecosystem and be exposed to their ads.
… we just don’t realize it. If you think about it, most of the social network services are specialized RSS Readers that combine consuming with creating. (Just to be clear, these social networks don’t provide RSS feeds, what I’m saying is that what they do could be done with RSS feeds.)
Take Facebook, for example:
If you follow someone, you’re subscribing to their RSS feed.
If you like a page, you’re subscribing to their RSS feed.
If you become friends someone, you’re subscribing to their RSS feed and vice versa.
If you view your timeline, you’re looking at all posts by your subscriptions (usually modified/filtered by Facebook).
If you post something, it’s added to your RSS feed and the people who are subscribed to you (via follow or friendship) get your post in their feed.
Twitter is similar, they just limit the post format to “status”. Instagram limits the post format to “image”. Tiktok to “video”.
Easily reachable and searchable user base (= audience).
Easy account creation (just sign up here).
They combine consuming with creation.
I see a possible solution in WordPress. There are many options to get WordPress hosting with your own domain. With the Friends Plugin you can then combine consuming and creating. The Friends plugin allows you to consume the web your way, WordPress is a well established way of creating content.
By using post formats, you can also create different types of content and consume the same kind of incoming content combined. See the screenshots above, showing the main, combined feed, an image feed and a status feed.
Also, commenting on posts is built in to WordPress. With a friendship based approach you can even open up comments just to friends, which can reduce the usual “spam problem.”
What’s still missing for is the convenience of single-purpose apps. The cool thing is that these apps would talk to your own server which handles retrieving of followed content vs. this being relayed to a third party (who then knows the follow patterns of everyone on their platform). With Sunlit, micro.blog has implemented something like this for photo sharing inside their micro.blog platform but I believe this could be done for “RSS” as well.
The Indieweb movement follows very similar ideas to what I described above. The concept of webmentions allows you to respond to a post by posting to your own server, sending a ping to the original article. While the WordPress + Friends approach might be a bit more integrated, I see webmentions as a reasonable bridge between the worlds.
All in all, I believe having a personal blog is good for the health of internet. It’s unfortunate that in their history, personal blogs have this huge focus on “being public.” I believe it is equally well suited to be a place for more private communication, and especially a place where you can consume the web the way you like.
The one thing I didn’t want to do, though, is to connect my site to WordPress.com. For the most part because I didn’t intend to use any of the functionality that requires the WordPress.com connection.
The difficulty in this: normally, you can’t actually use Jetpack until you connect the site to your WordPress.com account. This behavior is in place so you can enjoy a friction-less experience after the connection is established (i.e. you can activate any of its features whether or not it needs the connection).
In my case, the connection is not needed for using the Slideshow block since it works with the local media library.
So, I present not a hack but an official way to use Jetpack without a WordPress.com connection: it’s called Offline Mode.
You activate it by adding a constant or filter to your wp-config.php, for example:
define( 'JETPACK_DEV_DEBUG', true );
While it is intended for local installs and actually development, it is useful if you just want to use a single feature of Jetpack that doesn’t require the connection.
Many people say that Jetpack is slow because it’s so big. It is indeed huge from a file size and feature perspective, but also it’s very optimized, so that it will only load the PHP or JS code it needs. The other files lay dormant in your file system and don’t contribute to the loading or rendering time of your site.