personal software etc - customized tools for thought, probably self-code-customized

Alexander Obenauer term/frame around his OS/environment experiments, not unlike ObjectBrowser idea.

Tools for Thought dev https://alexanderobenauer.com/ (more)

Automerge is a library of data structures for building collaborative applications. (collaborationware) https://automerge.org/ (more)

InkAndSwitch: This is a simple collaborative Markdown editor built in React, with inline format preview and inline commenting. It's built on automerge and automerge-repo for CRDT-based storage and sync. It uses Codemirror for markdown editing UI, and automerge-codemirror to connect to Codemirror. https://github.com/inkandswitch/tiny-essay-editor f you visit the root domain the app will make a new doc. Or you can hit the New button. Once you have a doc, the URL will update with a doc ID. If you share that URL to another browser/device, it should sync live. Hold on to the URL if you want to come back to that doc! (more)

chronological ordering of events (more)

The biggest vision here is to mix the Wiki Name namespace idea with the use of Structured Data. So, instead of Bill Seitz being just a document page, it's a contact record, which of course has a note field. It's a PIM with easily-generated Intertwingularity. (initial thoughts 2002) (more)

Andrew Huberman (born September 26, 1975) is an American neuroscientist and podcaster. He is an associate professor of neurobiology and ophthalmology at the Stanford University School of Medicine. Since 2021, he has hosted the popular health and science focused Huberman Lab podcast. The podcast has attracted criticism for promoting poorly supported health claims.[2][3][4][5][6] Huberman has promoted and partnered with health supplement companies. https://en.wikipedia.org/wiki/Andrew_Huberman

I built a Lenny chatbot using GPT-3. Here’s how to build your own. Lenny Rachitsky: Last month, Dan Shipper (co-founder and CEO of Every) launched a chatbot trained on the Huberman Lab podcast, and I was blown away. I pinged Dan to see what it would take to build something like this for my newsletter content. Dan walks us through the basics of AI and GPT-3, how to set up an environment to play with the API, and how to train it on your own data. (more)

Zvi Mowshowitz: AIs Will Increasingly Attempt Shenanigans. Apollo In-Context Scheming Paper Details (more)

InkAndSwitch: OS of the future and universal version control. In this dispatch, we wanted to spotlight the work of Alexander Obenauer who’s been a Researcher-in-Residence with us since last year and introduce our new research project (more)

Alexander Obenauer on LN 038: Semantic zoom. earlier constructions of this environment had two to three view definitions for items (small, large, and full screen). The latest, as seen in this demo, allows for view components within one item view definition to swap out depending on the space available. This allows for the physicality and fluidity that this latest experiment required. (more)

Zvi Mowshowitz: AI #89: Trump Card. (more)

Alexander Obenauer on LN 040 venerable hyperlink. Earlier this year, I published OLLOS, an experiment in which all of the things in my digital life are organized into one long timeline. There’s an important benefit of this arrangement: things are naturally grouped with other things that were created, or that happened, around the same time. This implicit association matches one that runs deep in how we structure our memories and plans of things along the self-organizing dimension. (more)

Martin Cagan: Founder-Style Leadership. At this point, many people have heard about, and/or shared their thoughts on the “founder mode” discussion kicked off by the Paul Graham essay. I weighed in on this myself earlier in the article Coaching Founder Mode. (more)

Zvi Mowshowitz: AI #90: The Wall. As the Trump transition continues and we try to steer and anticipate its decisions on AI as best we can, there was continued discussion about one of the AI debate’s favorite questions: Are we making huge progress real soon now, or is deep learning hitting a wall? My best guess is it is kind of both, that past pure scaling techniques are on their own hitting a wall, but that progress remains rapid and the major companies are evolving other ways to improve performance, which started with OpenAI’s o1. (more)

Alexander Obenauer on LN 036: Free and easy organizations and associations (associative). The itemized environment is home to all of your items — notes, tasks, emails, podcasts, projects, websites, articles, and so on. They can be gathered and used together, regardless of type or source. Breaking down the boundaries we experience today between our various apps (and the data they hold) is an intentional and core aspect to the itemized OS. (more)

Alexander Obenauer on Heron project. Heron is an applied research project investigating concepts in personal health informatics (PHR) for individuals with chronic conditions. (more)

Alexander Obenauer on LN 011: General purpose personal computing software. Today’s lab note is a bit of a departure from the previous ten. Rather than exploring demos, I want to explore some ideas and implications from the previous two. (more)

alexanderobenauer on OLLOS. An itemized personal computing timeline. (more)