Urgent.News

What's breaking now, across thousands of outlets.

AI

My AI Agent Moves Real Money. I Never Take Its Word for Anything.

I run an AI agent that operates a crypto wallet on BNB Chain. It mines tokens, claims free mints, and submits transactions on a schedule, including while I sleep. It is also — in the only sense that matters — untrusted. Not because it has misbehaved. Because "the agent said so" is not evidence. Every action it takes has to survive verification against the blockchain itself before anything gets…

The author runs an AI agent that manages a crypto wallet on BNB Chain. The agent carries out various tasks, such as mining tokens, claiming free mints, and submitting transactions, even while the author is asleep. However, the agent is not to be trusted, as its actions must always be verified against the blockchain before any transactions are signed.

The author explains the verification process in detail, emphasizing the importance of checking the mining proofs, transaction inputs, and contract claims. For instance, each mining proof is re-verified three times: by recomputing the digest, checking the live target, and verifying the used-proof registry. Only verified candidates are then batched for submission.

Additionally, before signing any transaction, the wallet creates a preview of the exact call, which is simulated against the current chain state to ensure that it meets the specified rules. If the preview deviates from the expected outcome, the transaction is halted, and the deviation is investigated before proceeding. The author also highlights the importance of reading and trusting the contract itself over marketing claims.

They provide an example of a free-mint promotion where the contract did not actually offer a bonus, despite the marketing copy suggesting otherwise. The author also stresses the need for simulations to be run with realistic gas prices, as simulations running at a gas price of zero can lead to incorrect fee calculations and transaction reverts.

Finally, the author mentions a specific project called UNSOLVABLE, which requires agents to solve complex mathematical problems to earn a permit, rather than simply claiming a mint.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

How to Create a Logo with AI for Free

I'm not a designer. The first time I needed a logo, I proved it to myself: I opened a design app, stared at a blank canvas for ten minutes, and closed it again.

  • Provide key details about logo in brief, taking only five minutes
  • Choose 2 AI logo generators like Canva or Microsoft Designer
  • Specify logo details in prompt, avoid photos and slogans

ChatGPT vs Gemini: Which Is Better in 2026?

I use ChatGPT and Gemini every single day, and people keep asking me the same question: which one is better? After a year of switching between them for writing, research, coding help, and everyday…

How to Document a REST API with DocStar: Let Your AI Agent Draft It

Documenting a REST API used to mean days of copying routes, parameters and example bodies into a docs tool. With DocStar, your AI coding agent does that part.

  • Connect coding agent (Claude Code, Cursor, Codex) to DocStar
  • Review, test, publish interactive API reference with hosted MCP server and CLI

More from Sunday 15 November →