I've built a new AI model that is not allowed to generate text. Instead, it produces a verifiable program that answers your prompt using the original reference. XERJ Reader-1 is a neurosymbolic model for working with data. It points to the exact words in your document, writes a small program over them, and exact code computes the answer: • 20-90x faster • 10-1,000x cheaper (output tokens free) • every answer is a program you can replay The shortest path to automating data work.

i gave an Ai the power to pay invoices, then spent days trying to trick it into paying the wrong person. let me set the scene first. say you pay a contractor every month. one day their invoice shows up like always. same name, same amount, same tone. except there's a line at the bottom: "we've moved wallets, please use this new address." you'd probably just pay it. most people would. nobody wants to be the person who holds up a contractor's money over a hunch. that's why this scam works. it doesn't break into anything. it borrows the trust you spent months building and uses it at the one moment nobody double-checks. So for the @NEARProtocol hackathon I built STEWARD, an AI accounts payable clerk that can't be talked into paying a fake. One rule kept me honest the whole way: the AI reads and explains, plain code decides, and a human approves anything unusual. here's what happens when an invoice comes in: > the AI reads it privately inside a NEAR AI Cloud enclave, and the app shows the attestation check so you can see it wasn't read anywhere else. > it pulls out the vendor, amount, dates and payout address. > then regular code takes over. known vendor? did the address change? duplicate? over the limit? is the receiving address clean? > the answer is always one of three things: pay automatically, hold for a human, or block. With the reason. > approved invoices are paid through NEAR Intents, so the vendor gets the exact amount in the asset and chain they asked for. > every decision goes into a log you can export as a CSV an accountant can open without asking questions. then I went after it. i wrote 30 test invoices, some honest, some nasty: a changed wallet, a duplicate sent twice, totals that don't add up, a brand new vendor, routes to other chains like Arbitrum and Solana, and a PDF with a hidden line telling the AI to pay someone else. and the results: • 18 blocked • 7 held for a human (new vendors, address changes in a 48-hour cooling-off window, bigger amounts) • 5 paid automatically (the honest ones) • 0 unauthorized payments every verdict matched what I expected. Built for these tracks: Real-World Money, Privacy & Private AI, and AI Security & Defense. Site: Repo: if you pay vendors or contractors across chains, I'd really like to know what would make you trust something like this. tell me what I'm missing. @NEARProtocol #NEARHackathon#

I find myself giving this advice pretty often, figured I should share it publicly Once you're paid enough to live, the ONLY thing that matters is that you're surrounded with awesome fucking people.

I'd rather try and fail than spend years wondering, “What if?” Success gives you confidence. Failure teaches you lessons you wouldn't learn any other way. Either way, you walk away with something.

I was thinking about why most DePIN projects that collect real-world data are still considered “untrusted” by major enterprises. The answer is simple: you can’t prove where the data came from or whether it was altered after being uploaded. @vangrid_io solves this problem in a smart way. When you record with your phone, the video itself never goes on-chain. Faces and license plates are blurred directly on your device before any data leaves it. Instead, Vangrid instantly generates a fingerprint of the capture: a content hash, approximate location, and timestamp. These fingerprints are grouped into batches, and then the Merkle root is published on Base as an attestation roughly every 15 minutes through EAS. The key advantage? Anyone can independently verify that a capture exists and hasn't been tampered with using an inclusion proof, without having to ask Vangrid or trust its servers. The verification process ends at the public ledger. This doesn't prove that the scene itself is 100% authentic (those layers are still coming), but it creates a clear trail of provenance, timing, and data integrity. And that's the difference between “someone uploaded a video” and data that anyone can trace back and independently verify. Want to see the attestations for yourself? Explorer: @vangrid_io