Ansar Kanhiroli

Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.

@karpathy basically a smart local Notebook LLM?

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.

@alexgarcia_atx @SendToNotion

Mailchimp was acquired by Intuit for $12B. But first, it was a side hustle for 7 years. Then in 2009, Mailchimp's userbase exploded from 85k to 450k users in one year. Here are the 3 tactics that led to acquiring 365k users:

@BDUTT @iamsrk @washingtonpost Really nice article @BDUTT

Once upon a time @iamsrk was a symbol of hope, a story of all that was bright, brilliant and possible in India. Now his own journey has come to be a symbol of all that is being corroded. My piece for @washingtonpost #AryanKhan washingtonpost.com/opinions/2021/…

I guess Akamai is down, none of the apps are displaying any images 🥴

@CNBC Hoped for better and more socially impactful startup ideas from the Bay Area. This may need millions if not billions to become the norm and even then the prominent use cases most likely will be in defense (aka wars). World needs more human centric and socially valuable ideas!

Bay Area start-up Xwing took us for a test flight, where the pilot didn’t touch the controls once. When will pilotless planes become the norm? Watch the full video here: cnb.cx/2Qo7IYX

Maserati mc20 - the game is resetting... #MaseratiMC20 #supercar #supercarblondie - review this please! caranddriver.com/photos/g339583…..

tomsguide.com/news/iphone-12…. #iphone #iphone12

Hello world!

@AqeelaThx, Your Order# is 99867443567, click here for more details

@Aqeela53825692Thx, Your Order# is 99867443567, click here for more details

@ansar_abd#HelloWorld back to you!

@ansar_abd#helloworld back to you! -

@ansar_abd #helloworld - my personal TweetBOT

@ansar_abd#HelloWorld back to you!

@ansar_abd#helloworld back to you! -

@ansar_abd#HelloWorld back to you!

@ansar_abd myPersonalTweetBot #helloworld back to you -

@ansar_abd#HelloWorld back to you!

@ansar_abd myPersonalTweetBot #helloworld back to you -

@ansar_abd#HelloWorld back to you!

@ansar_abd myPersonalTweetBot #helloworld back to you -

@ansar_abd#helloworld back to you! -

@ansar_abd#helloworld back to you! -