44 entries
Watching Maggie Appleton's GitHub Universe talk on agent collaboration. Running notes on alignment as the new bottleneck, the ACE environment, conversations under the hood, and a comparison with Engelbart's NIC.
Tommi's personal site, framed as 'a perpetual work in progress' — a digital garden built around identity rather than credentials, with explicit anti-surveillance and indie-web commitments. Links community workshops, decentralised internet practice, and a Leibniz-style acceptance of incompleteness as core to what the site is.
Issue of the Convocat newsletter Creative Prompts: garden updates, news for content professionals, seeds, and what I'm reading.
I rebuilt Karpathy's LLM wiki on top of my digital garden content, with interesting results.
A technical side-by-side of Andrej Karpathy's LLM wiki approach and how I work with AI on this garden. Same tools, different philosophy.
A chatty intro to my digital garden: how I use Claude Code to build an online space for thinking and writing in public.
How Claude invented a book by my competitor, why it happened, and the rule added to prevent it.
Why this site is called a garden, what plant growth means for ideas, and how the metaphor shapes every editorial decision.
Extracting meaningful entities and relations, combining thematic analysis with TAO topic mapping in three passes.
On the tension between cultivating a tidy digital garden and letting the chaos of ideas coexist. How AI-assisted growth pulls at the time and attention I'd rather spend writing.
Five short experiments validating new Claude features (March 2026 release) on the digital garden. Practical demos for conversation designers.
Seven themes and one emerging pattern discovered by loading all 244 garden files into a single context window with no prior structure.
What happens when you start from embeddings instead of reading? Comparing cluster-based discovery against the fresh thematic analysis.
Task-based reference for maintaining this digital garden: writing, tagging, linking, mapping, sharing, publishing.
Using the garden's own knowledge graph to find relevant external content, papers, and articles.
A lifecycle metaphor for how content enters, matures, decays, and recycles in the garden.
How the explore map got stable positions and pinned territories, so the landscape doesn't shift on every rebuild.
How hub/develops relations replace tag-based project structure with an explicit ontology, and what that means for the three kinds of connections in the garden.
Three layers of automated testing: content validation, build verification, and Playwright E2E. Why each layer exists and what it catches.
Design for integrating the book recommender with the garden library, making it the single source of truth for all book data.
A personal book recommender that matches candidates against my library and garden interests. No AI, just logic and situational vibe chips.
Audit of 40 unread and in-progress books with status labels, reading patterns, and calibration data for the recommender.
Why embedding models cluster documents by format instead of topic when content lengths vary, and what to do about it.
Design document for an /explore page that lets visitors walk through the garden visually, using semantic maps, serendipity, and trails.
Running LLM-based key phrase extraction on all 92 garden items. What the results reveal about phrase overlap, short-text limits, and the role of key phrases in the knowledge graph.
What key phrase extraction is, how it evolved from word counting to LLM prompting, and which approach fits a small multilingual knowledge garden.
How to go from "everything is related to everything" to a useful set of link candidates. Data analysis, filtering strategies, and the research behind them.
Extract key phrases from 10 garden items using Ollama, compare LLM-based extraction with YAKE.
A non-coder's guide to text embedding models, from word counting to semantic understanding, surveyed for use in a personal knowledge garden.
Research into making the garden smarter about its own connections, from automatic backlinks to a full world model.
Reading notes from Apple's Saga papers on building knowledge graphs at scale, and what transfers to a personal digital garden.
Can a chatbot-style UI work without generative AI, using decision trees, hyperlinking, and serendipity instead?
Academic research on embeddings hasn't caught up with how PKM tools actually use them. There might be something worth writing here.
Should a digital garden be searchable and useful, or is there beauty in letting people explore?
Apple's hybrid batch-incremental knowledge graph platform. Key inspiration for building smarter connections in this garden.
How to install and run embedding models locally using Ollama, compare three models on garden content, and run a full-scale embedding pass.
A changelog of features and decisions made while building this digital garden.
Why I built a digital garden: non-linear thinking, early web nostalgia, and the need for a personal space on the internet.
What if I wrote a comprehensive guide on how I built this site?
What design principles shaped this site, and why do they matter?
The practice of sharing unfinished thoughts openly.
What makes a digital garden different from a traditional blog?
A comprehensive overview of the digital garden concept and its evolution.
Sketchnotes of the Voicelunch session with Brian Roemmele, the best voicelunch I never attended.