Al Harkan

Ever-growing threads on notable AI developments for research, education, and software engineering —fields that I've been paying close attention to in the past 5 years:

The endgame of AI advancement (in education) would be when it can finally explain anything in motion graphics. It's already proficient at searching references & explaining in text & voice. And models like Sora & others are attempting video mode. However, the real bar to clear is when they can present any topic using approaches like Manim (@manim_community) for math.

Sharp minds and critical thinking, that's always been the purpose.

It'll be bad if we have a generation that's reliant on & accustomed to this technology from an early age, without knowing what the tool really is. I've seen people blindly trust what these "AI" systems generate, and that's not what schools are for.

We should teach students in schools how LLMs and "AI" systems work. Not the technicalities and math, but how it works, just like we teach human biology. The technology is already deeply embedded in our learning process, so it's important to educate them on it.

We're still super early in the agentic browser and OS space. I'm starting a running list for the notable ones here.

Three years since the first flight of Starship, the next generation is here. New ship. New booster. New engines. New pad and new test site. SpaceX engineers are working to solve one of the most difficult engineering challenges in history: developing a fully, rapidly reusable rocket

@github alharkan7.github.io

GitHub Pages is the easiest way to host your static sites for free. If you’ve already shipped yours, drop the link in the replies👇and show us what you built! 🌍

I sequenced my genome at home, on my kitchen table. I wrote up exactly how I did it - the equipment, protocol, theory, and cost: iwantosequencemygenomeathome.com

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.

Good morning, world! 🌎 We have spectacular new high-resolution images of our home planet, all of us looking back through the Orion capsule window at our Artemis II astronauts as they continue their journey to the Moon.

"We have to remember that what we observe is not nature herself, but nature exposed to our method of questioning."

Every time AI pushes the boundaries of science and finally brings a net positive to human knowledge: Exhibit #1 – C2S-Scale, a small open-source LLM that generated a novel hypothesis about enhancing antigen presentation in cancer cells.

Grok has finished reviewing the entire corpus of active EU legislation. It recommends deleting 89%. @_FriedrichMerz

For the future of high-quality, personalized education at scale, this is a good start.