Ayan Das

@Prof_Cheems it's definitely him

😭🤣

@TSLA_inside_ Cute. Now try Swindon’s Magic roundabout in UK.

The most difficult roundabout in the Netherlands, Keizer Karelplein in Nijmegen. No effort for FSD. $TSLA

@Rainmaker1973 if they are same, I’ll take the KFC

Can you believe it? 1,500 calories can look completely different.

@aaronp613 why/how tf this app is still on your phone ?

How/why the fuck is this app still getting bug fix updates

@iTejasJagtap but we want info about his daughter, specifically her instagram ID 🤣

Jameel Jamali's character is actually based on Altaf Hussain, not Nabil Gabol Altaf has only one daughter. He got married at the age of 47 with a 27 year old Baloch woman. He was accused of working for R&AW. Little to no public info about his daughter.

@RealestMemes_ 🤣🤣🤣🤣

@twholman also true for any cool threejs projects

The first rule of html-in-canvas api, never share anything but a video of your html-in-canvas demo.

@ajansJargon so we all come with a wrapper ?

Doğum sırasında amniyotik kesesi yırtılmayan bir bebek, doktorların müdahalesiyle dış dünyayla tanıştı.

Precisely. The second last paragraph is 💯% on point.

@ryanels change the font and it'll work

Can you help me figure out why my code isn't working? 🤔

This could not have come at a better time when countries are struggling with energy security. x.com/i/trending/204…

@sciencegirl I skipped the last part and almost concluded that the bird uploaded the video

A bird snatched a phone from a girl’s hands right in the middle of her recording

@Sastianie well to be fair, she had 2x3 jobs

she had ONE job i’m in tears😭

@Samaytwt let me guess it asks for min 8 yrs of experience

wtf I thought Vibe Coding is just a meme, you guys were serious?

This needs to be a bigger news. 🫡

@mohammad_i77884 ah, posted on April 1st -- good humour bro 🤣

This map relates to the history, prosperity, and glory of the Muslims of the Bengal region. This is where the glorious "Sultanat-e-Bangalah" was located. Greater Bangladesh will be established one day, InshaAllah. 🇧🇩

@pixelated_cat_ @vintagemapstore In Bengali, we say "mishawr" and I never understood why. Now I know

Countries whose local names are extremely different from the names they're referred to in English

@karpathy no shit, I was doing the same thing for a while now

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.

CMake is the worst thing that happened to C++

@YearOfTheKraken Bro is playing the long game, as he should, as he was trained for. 🫡

Real Life Jameel Jamali, Nabil Gabol, is out here posting reels on Instagram with Dhurandhar 2 Music "Dil me Zakhm khaate hain, Jaan se guzar jaate hain." 😭😭😭