commented here on h. "Wrt permanence, my own h. bookmarks and annotations flow directly into my local notes, through the h. API.

The h. software is open sourced, so theoretically one would be able to run their own instance of it. Except for the social function of it. Like you I follow Chris Aldrich annotations feed (which is how I ended up here), and several others. When others bookmark the same stuff I do but use very different tags for it, is where it gets interesting. Like years ago in the del.icio.us bookmarking service, the difference in tags signifies a social or sectoral distance. Basically you're finding a sliver of overlap between two different mindsets / contexts / interests. I then can add those people to the feeds I follow."

personal tools built with vibecoding by Simon Willison Resulting tools are mostly HTML and javascript, some python.

• [ ] return

Simon Willison vibe coded over 100 personal tools in 2025. This chimes with what Frank and Martijn were suggesting. Up above he also indicates that it is something that became possible at this scale only in 2025 too.

https://web.archive.org/web/20251230193244/https://www.docker.com/blog/private-mcp-catalogs-oci-composable-enterprise-ai/ via [[Lee Bryant p]] this article focuses on 'playlist' style remixing of MCP servers for the enterprise. In light of the disc within Digitale Fitheid, around [[Eindelijk weet ik wat ThetaOS is een Life Lens System (LLS)]] etc., I'm more interested in shareware style distribution of MCP servers p2p and in/between communities

https://web.archive.org/web/20251228112323/https://world.hey.com/martijnaslander/het-rendement-van-een-life-lens-system-emergentie-in-mijn-praktijk-377f68ad

[[Martijn Aslander p]] over zijn lifelens systeem en wat meer praktisch inzichten

Android Studio is the official IDE for Android app dev. There is a MacOS version.

#openvraag is this usable to code up a personal app for mobile?

Making personal tools makes generic ones obsolete. Yet, the generic ones do serve as starting point for inspiration and design choices. Personal iterations on top of what went before.

[[Martijn Aslander]] has made several personal tools for his iphone.

The cost of lack of skills is not just in the individual knowledge worker, it gets externalised to others to fix it, or multiplied in groups waiting on you to get something working. The incompetence spreads out.

knowledge workers are the largest group of people who don't know their own tools. Vgl [[Kenniswerk is ambacht 20040924200250]]

baseline digital fluency not reached

All the hype on the potential of AI, likely the potential of just knowing how to use what we have is bigger

Knowing your tools is key to knowledge work, know your computer. It's not cute to play tech-incompetent

Key statement. PKM is about ideas and knowledge (at least to himself, my PKM combines that with practice) "I need something that combines my entire personal reality" Ppl, locations, events, transactions, opportunities, ideas, projects etc.

The tech is straigthforward: sqlite, node.js and html/css. The value is the combination of different sources into personal tool.

Yes. I use lots of small local html/php pages. Also webforms to search websites elsewhere, without going there. I had local pages to browse local image files in the 90s. I started writing html by hand in '93 and still do for local stuff. I do use a local on-device webserver though, as I include php.

https://web.archive.org/web/20241017043750/https://alexwlchan.net/2024/static-websites/

I like this idea of having static html as page to explore folders, I had that in the 90s to better search for image files. Author offers no clues as to how he uses the affordance it provides though, in terms of 'showing the metadata' they care for and the little bits of extra functionality. And I wonder about the effort involved when adding new files. Presumably new files are added manually too, otherwise it's not 'static html'. Stores files by year, type and first letter of file name. That makes no immediate sense to me in terms of finding things back. Then again I never understood why you would have folders for file types. It's like sorting items on the type of box it came in. Good example though of making your computer your own.

https://web.archive.org/web/20240712191025/https://x28newblog.wordpress.com/2024/07/12/personal-ai-beyond-the-distractions/

Matthias Melcher on (personal) AI and which affordances it may provide or not. Vgl n:: Mark Meinema's remark about how it os much better at switching role than a human (explaining the same thing for a 5yr old or expert)

[[Lee Bryant]] links to this overview by Simon Willison of what happened in #2023/ in #AI . Some good pointers wrt [[ChatPKM myself]] dig those out.

this. Vgl [[CPUs, GPUs, and Now AI Chips]] hardware with ai on them. Vgl [[Everymans Allemans AI 20190807141523]]

Yes, if I could run my own notes of 3 decades or so on an LLM locally (where it doesn't feed the general model), that I would do instantly.

Not just bubble, it will be the FB timeline. Key here is agency, and design for human biases. A model is likely much better than I to manage the diversity of sources for me, if I give it a starting point myself, or to see which outliers to include etc. Again I think it also means moving away from single artefacts. Often I'm not interested in what everyone is saying about X, but am interested in who is talking about X. Patterns not singular artefacts. See [[Mijn ideale feedreader 20180703063626]]

Appleton suggests agents to fact check / filter / summarise / curate and suggest (those last two are more personal than the others, which are the grunt work of infostrats) would become part of your browser. Only if I can myself strongly influence what it does (otherwise it is the FB timeline all over again!)

If these models become part of the browser, do we still need the browser as a metaphor for a window on the web, or surfing the net? Why wouldn't those models come up with whatever they grabbed from the web/net/darkweb in the right spot in my own infostrats? The browser is itself not a part of my infostrats, it's the starting point of it, the viewer on the raw material. Whatever I keep from browsing is when PKM starts. When the model filters / curates why not put that in the right spots for me to start working with it / on it / processing it? The model not as part of the browser, but doing the actual browsing, an active agent going out there to flag patterns of interest (based on my prefs/current issues etc) and organising it for me for my next steps? [[Individuele software agents 20200402151419]]

Yes, agency at the edges. Ppl running their own agents. Have your agents talk to my agents to arrange a meeting etc. That actually frees up time. Have my agent check out the context and background of a text to judge whether it's a human author or not etc. [[Persoonlijke algoritmes als agents 20180417200200]] [[Individuele software agents 20200402151419]]

This hints towards prompt-engineering, and the role of prompts in human interaction itself [[Prompting skill in conversation and AI chat 20230301120740]]

High Q use of generative AI will be about where in a creative / work process you employ to what purpose. Not in accepting the current face presented to us in e.g. chatGPT: give me an input and I'll give you an output. This in turn requires an understanding of one's own creative work processes, and where tools can help reduce friction (and where the friction is the cognitive actual work and must not be taken out)

https://web.archive.org/web/20230316103739/https://subconscious.substack.com/p/everyone-will-have-their-own-ai

Vgl [[Onderzoek selfhosting AI tools 20230128101556]] en [[Persoonlijke algoritmes als agents 20180417200200]] en [[Everymans Allemans AI 20190807141523]] en [[AI personal assistants 20201011124147]]

I wonder if it uses the W3C recommendation for highlighting and annotation though? Which would allow it to interact with other highlighting/annotation results.

To me highlighting is annotation, though a leightweight form, as the decision to highlight is interacting with the text in a meaningful way. And the pop up box actually says Annotation right there in the screenshot, so I don't fully grasp what distinction James is making here.