snehil wakchaure

Innovator | Problem Solver at Oracle.

[snehil wakchaure @snehilw]

@elonmusk @olivercameron ❤️

[snehil wakchaure @snehilw]

Deeply grateful for those who served and made the ultimate sacrifice. On this Memorial Day, heartfelt thoughts and honor to all who walked that selfless path. May their souls rest in peace. 🇺🇸

[snehil wakchaure @snehilw]

Excellent explanation on Flow and Diffusion models (MIT)! https://t.co/KVGarQCEOz

[Andrej Karpathy @karpathy]

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.

[Eyad @eyad_khrais]

https://t.co/i5L6UIPgH8

[NVIDIA Robotics @NVIDIARobotics]

Bring new robot testing environments to life with @theworldlabs and Isaac Sim. 🤖 If you can describe a world 🌎, you can start testing in it the same day.

Learn how to:
1. Export scenes from World Labs' Marble as Gaussian splats
2. Convert to USD using @nvidiaomniverse NuRec
3. Import into NVIDIA Isaac Sim
4. Add a robot and run the simulation

Read the guide ➡️ https://t.co/0kCSFIxhVC

#SIGGRAPHAsia2025

[Andrej Karpathy @karpathy]

As a fun Saturday vibe code project and following up on this tweet earlier, I hacked up an **llm-council** web app. It looks exactly like ChatGPT except each user query is 1) dispatched to multiple models on your council using OpenRouter, e.g. currently:

"openai/gpt-5.1",
"google/gemini-3-pro-preview",
"anthropic/claude-sonnet-4.5",
"x-ai/grok-4",

Then 2) all models get to see each other's (anonymized) responses and they review and rank them, and then 3) a "Chairman LLM" gets all of that as context and produces the final response.

It's interesting to see the results from multiple models side by side on the same query, and even more amusingly, to read through their evaluation and ranking of each other's responses.

Quite often, the models are surprisingly willing to select another LLM's response as superior to their own, making this an interesting model evaluation strategy more generally. For example, reading book chapters together with my LLM Council today, the models consistently praise GPT 5.1 as the best and most insightful model, and consistently select Claude as the worst model, with the other models floating in between. But I'm not 100% convinced this aligns with my own qualitative assessment. For example, qualitatively I find GPT 5.1 a little too wordy and sprawled and Gemini 3 a bit more condensed and processed. Claude is too terse in this domain.

That said, there's probably a whole design space of the data flow of your LLM council. The construction of LLM ensembles seems under-explored.

I pushed the vibe coded app to
https://t.co/EZyOqwXd2k
if others would like to play. ty nano banana pro for fun header image for the repo

[snehil wakchaure @snehilw]

https://t.co/XJcMR1U7OD

[snehil wakchaure @snehilw]

AI interpretability is without a doubt the most critical and time sensitive challenge of our time, and should be treated with a sense of utmost urgency. https://t.co/14or8K7Gas

[snehil wakchaure @snehilw]

These are some game-changing insights!

Tracing the thoughts of a large language model

- https://t.co/XJcMR1U7OD

https://t.co/ZeU05ZQZ3e

#artificialintelligence #llms

[snehil wakchaure @snehilw]

@werkman @MD_ata21 How would strk atm affect mstr

[Rowan Cheung @rowancheung]

I think China's second DeepSeek moment is here.

This AI agent called 'Manus' is going crazy viral in China right now.

Probably only a matter of time until it hits the US.

It's like Deep Research + Operator + Claude Computer combined, and it's REALLY good.

[Avi Chawla @_avichawla]

Traditional RAG vs. Agentic RAG, clearly explained (with visuals):

[snehil wakchaure @snehilw]

@PunterJeff @lindsaystamp3 @PunterJeff Please remind me if we covered MSTY in any of the TrueNorth episodes. I might have missed it if yes, trying to get information on it.

[snehil wakchaure @snehilw]

@PunterJeff @tomyoungjr How about Roth IRA?

[snehil wakchaure @snehilw]

@werkman How is this different than ATM?

[snehil wakchaure @snehilw]

@HermesLux @PunterJeff Thank you @HermesLux and @RyanJamesEgan7 !

[snehil wakchaure @snehilw]

@HermesLux @PunterJeff Can you explain when to sell CC on mstr? New to this

[snehil wakchaure @snehilw]

Happy sum(i**3 for i in range(10)) !