senad

@brysondech @TheMasters Let’s go!! Good luck.

Tuesday @TheMasters

@Flewellen727 💙

Tropicana Field, Gate 5 Opening Day 1999 with my Grandmother, Opening Day 2026 with my Mom #RaysUp

I must plant trees I will never know the shade of

“That’s @AndreTroutman on Talkbox” -@kanyewest

@Bottom_Creek @frontierism Why would God show us the stars if we weren’t meant to be among them

I use obsidian as a daily note. Then at the end of every day, Claude skills run to encode it, and sync it with info per project across all commits and issues. It encodes it into a daily summary, I have more than 3 months of daily summaries. Tracing back to links and finer details. Obsidian is Really awesome! Now to give agents their own vault, that’s interesting.

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

Liftoff of Artemis II

Just as you travel so that you can miss your home, you socialize so that you can miss your self.

@bigrobbbbbbbb Should only have golf legends/professionals be the broadcasters.

This is a major win for The Masters and golf in general #ShrinkTheGame

Vibe coding is more addictive than any video game ever made (if you know what you want to build).

@TcrsCntr @ShonenDailyZ @gogeta99885 Piccolo + dragon balls are connected. He absorbed Kami. Piccolo, the other namekians, have known Shenron for a long time.

@ShonenDailyZ @gogeta99885 Orange piccolo has actual lore on it compared to gohan pulling blanco out of his ass

The worst transformation in Dragon Ball. I don't understand how some people like this transformation.

@Cine_vichaar Think about the karaoke scene about once a week…

Peak Television

@beagleschmeagle Search Gabagool

Extremely rough start to the day

@sailaunderscore or Can’t Hold My Liqour

@sailaunderscore 30 hours

Every single real Kanye fan has the same favorite Kanye song, you can actually tell 100% of the time if someone is a real fan by asking them this.

The cowboy and the samurai are natural allies.

Was woken up at 4am bc it was too hot in the hotel room. Nano Banana gods saved the day. prompt: “create an image in English”

How me and Claude have been moving lately