Kryptonian retweeted
just read abt it today when going for @EFDevcon and this is exactly why financial sovereignty matters.
your money shouldn’t depend entirely on the health of a bank, the decisions of a government, or the promises of an institution.
for those of us building in this ecosystem, incidents like this should remind us why open networks like @ethereum @Bitcoin @Zcash etc matters.
self-custody, transparency, permissionless access, and verifiable ownership aren’t just technical features. they’re fundamental principles of an alternative financial system.
People shouldn’t have to depend on institutional promises when technology can give them verifiable ownership. Blockchains are build to solve this!!
Kryptonian retweeted
Your AI agent shouldn’t pay $0.01 USDC for {}.
Introducing PayCheck: pay for x402 APIs only if they work.
Standard x402 settles before the API responds. PayCheck checks latency and schema first, and charges $0.00 if it fails. Built for agents that pay for APIs using @PayBox.
the first PayBox Hackathon is live!
build a plugin for our marketplace and compete for $20,000 USDC in prizes
start here: developer.paybox.sh
Kryptonian retweeted
Demo Day hits tomorrow: six weeks of Vela builds, one live stage.
TOMORROW IS THE DEMO DAY!
On Thursday, October 15 at 1PM UTC, 9 startups from the @horizenglobal Acceleration Season will pitch live in front of our audience and judging panel.
The startups pitching at Demo Day are @velum_horizen, @AustralFinance, @Detentlabs, @layrslab, @GachaGalaxyHQ, @Noct_finance, @zCredLabs, metaMe and SYNSEMA.
Kryptonian retweeted
TOMORROW IS THE DEMO DAY!
On Thursday, October 15 at 1PM UTC, 9 startups from the @horizenglobal Acceleration Season will pitch live in front of our audience and judging panel.
The startups pitching at Demo Day are @velum_horizen, @AustralFinance, @Detentlabs, @layrslab, @GachaGalaxyHQ, @Noct_finance, @zCredLabs, metaMe and SYNSEMA.
DEMO DAY — HORIZEN ACCELERATION SEASON
The day is here. Next Thursday, October 15, the startups selected for the @horizenglobal Acceleration Season take the stage for Demo Day.
After six weeks of building on Vela, each team will pitch live to the audience, VCs, angels and a group of guest judges. Their moment to shine.
Kryptonian retweeted
Money moves in batches. Work doesn’t.
Introducing OpenFluid — streaming payments on @CantonNetwork.
Payroll. Subscriptions. Grants. Vesting...
Continuous. Private. On-ledger.
The future of money flow starts here 🌀
Kryptonian retweeted
Launching GateLink = OAuth for your crypto wallet.
Token allowlists ✅
Protocol control ✅
Spending limits ✅
Auto-expire ✅
Deployed on X Layer testnet. AI agent ready via MCP + Onchain OS skills.
The missing permission layer for agentic wallets.
#BuildX @XLayerOfficial
Kryptonian retweeted
let me explain what Karpathy just shared
he’s spending way less time using AI to write code and more time using it to build personal knowledge bases
the full breakdown:
→ he dumps raw sources (articles, papers, repos, datasets, images) into a folder. then has an LLM organize them into a wiki… a collection of markdown files with summaries, links between related ideas, and concept articles that connect everything together
→ he uses Obsidian as his frontend. he views raw data, the organized wiki, and visualizations all in one place. the LLM writes and maintains the entire wiki. he rarely touches it directly
→ once the wiki gets big enough (~100 articles, ~400K words on one recent research topic)… he just asks the LLM questions against it. no RAG (complex retrieval system) needed. the LLM maintains its own index files and reads what it needs
→ outputs aren’t just text. he has the LLM render markdown files, slide decks, charts, and images… then files the outputs back into the wiki so every question he asks makes the knowledge base smarter
→ he runs “health checks” where the LLM finds inconsistent data, fills gaps using web search, and suggests new connections and articles. the wiki cleans and improves itself over time
→ he even vibe coded a search engine over his wiki that he uses directly in a browser or hands off to an LLM as a tool for bigger questions
→ his next step: training a custom model on his own research so it knows the material in its weights… not just in the context window
most people use AI to get answers.
Karpathy is using AI to build his own ‘Jarvis’ via compounding knowledge systems that get smarter the more he uses them
the difference between asking ChatGPT or Claude a question and having a personal research engine that grows with every session is the gap most people haven’t crossed yet
and this is where it gets really powerful
not replacing your thinking but organizing everything you’ve ever learned into something you can query or create with forever
if you’ve been using CLAUDE .md and context files in Claude Code… this is that same idea at a much bigger scale
if you’re doing any kind of AI work or deep learning on a new topic right now…
this workflow is worth studying closely
you’ll want to adopt it yourself
this is one of AI’s brightest minds after all. we’re all better off listening to him.
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.
Kryptonian retweeted
1/ The text version was a massive public good, so I decided to bring it to life. 🌐
turned it into a modern web app that makes crypto fundamentals actually intuitive to learn. 👇
1/ Today I’m releasing an open-source book in collaboration with @FrankResearcher that I wish existed when I started in crypto. It’s split into 15 chapters covering everything that matters - from BTC to DeFi, MEV, Hyperliquid, quantum resistance, etc.
github.com/lawmaster10/howcr…
Kryptonian retweeted
Today → Immersive Experiences Jury.
Builders showcase gaming, identity, and creative projects powered by Hedera.
@The_Hashgraph and the @Exponential_Sci Foundation bring innovation and imagination together on Nov 13.
Kryptonian retweeted
I'm giving Claude Code for FREE
(yes the world's best AI -- at no cost at all)
My mission is to get the next billion people to write great software, but so many are constrained by costs.
We solved this by combining AI with ads (only contextual and relevant ads, no spam).
In return, you get the best AI models without needing a credit card.
For the next batch, I will choose 500 people randomly who have done the following steps:
1. Comment "GIVE ME SANTA CLAUDE" below
2. Like and retweet this
3. Follow @NamanyayG and @supermemory
4. Sign up on the link in the next tweet
Watch this quick video to understand how it works!
Kryptonian retweeted
i built a tool that allows me to clone the brain of any youtuber…
i used it on alex hormozi so i can ask him business questions at 3am and get answers word-for-word like he'd give them
works with anyone: gary vee, naval, graham stephan, any creator in your niche
i put together:
- the tool that uploads entire channels automatically
- my 5-minute setup process
- prompt framework for answers that match their exact style
RT + reply 'MENTOR' and i'll send you everything (must follow so i can dm)
Kryptonian retweeted
🤝 Premium Web3 domains shouldn't just be for whales. Pool funds, fractionalize ownership, and buy together using Domie’s community deals.
Get ERC-1155 tokens for your share and split profits automatically. Own more, together!
Kryptonian retweeted
📢 Introducing Domie: The first platform that makes your Web3 domains Google-searchable, tradeable in-chat, and accessible through community deals.
Three game-changing features, one revolutionary platform. Welcome to the future of domain trading.































