Finding bugs in smart contracts is an information problem.
To catch one, you must know what the code does in each module AND at the interfaces, and explore the threat space.
Two things one agent with a limited context window struggles with.
We're building Azimo to fix it 🧵
Hey! We're building Illumina, an autonomous vulnerability discovery system, and are looking to validate it against real-world codebases. We're not looking for jobs, but exploring potential collaborations to test and improve the system. Would be great to connect if interested and tell you more!
I was buying lunch today at my favourite tavola calda:
> Transaction rejected.
Revolut is down.
Hunger mixed with anger and concern.
Was it a cyberattack? There's no evidence of that so far.
Only a proper post-mortem can tell us what happened to Google Cloud.
One thing is clear: I'm even more locked in on building @SunnyGoesRogue, our agentic cybersecurity system for continuous auditing and vulnerability detection. 🔒
@superteamITA Born in Como and having worked on Solana before, this one really touched my heart. So psyched to see the ecosystem growing in Italy. Let’s gooo! 🇮🇹🚀
Following @BerkeleyRDI MOOC on Agenting AI. Since llm-is-life, we got inspired to start a series of posts: "A bunch of cool things about AI a day".
Lots of cool things today: training pipeline, evaluation and systems. Buckle up!
🚀Day 1: LLM Agents Overview by @yanndubs 🚀
Circulating supply is a key input into token valuation and dilution analysis, but forecasting how it will evolve is rarely straightforward.
This is one of the projects I’ve been working on at CryptoEconLab: making supply forecasting systematic, data-driven, and applicable across tokens.
Here’s the model in action for TON.
Your token’s price is only half the story.
Changes in circulating supply can reshape dilution, sell pressure, liquidity, and thus valuation.
We built a system that automatically creates a circulating-supply digital twin for any token, simulating 1,000 possible futures and validating the forecast against real on-chain data.
Here’s what it looks like for TON: its observed supply, ~9 months later, remains inside the projected bands.
Interested in forecasting the circulating supply of your token?
Contact us at [email protected]
Agents find bugs at an unprecedented rate. Is the pre-AI market for bug brokering going to be able to sustain the massive increase in mined bugs? Should this market be decentralized?
Proof-of-exploit lets an agent prove knowledge of a working exploit without revealing it. Can we leverage this capabilities to create an arena for bug-finding-agents and bug-patching-agents to autonomously interact and make software more secure for all?
Final call for audits to @juiceboxETH's upcoming "AI-hardened" V6 protocol.
https://t.co/3Bif8ExqEK
give the AUDIT_INSTRUCTIONS.md file to your favorite LLM and have it try to come up with addressable issues.
Thank you!!
NEW CHALLENGE ANNOUNCEMENT
Announcing the Energy Arbitrage designed in collaboration with @cryptoeconlab
It's been on testnet for over a month and live on mainnet next week!
So what is energy arbitrage and why does it matter?
AI is eating electricity faster than grids can supply it
The algorithms that decide how grid-scale batteries charge and discharge are becoming some of the most consequential algorithms on Earth, and until today they've been locked behind closed doors.
Great to bring a cryptoeconomist's lens to the agentic economy at @EthereumZuri.
The thesis: agents need rules, not just rails.
Mechanism design is how you write those rules and blockchain is the shared infrastructure where we should write them.
Thanks to everyone who joined. More to come.
Missed this at Ethereum Zuri?
“The Rules of the Agentic Economy: A Mechanism Design Perspective”
by Luca Nicoli (@_LucaNicoli).
As AI agents transact and act in the real world, who sets the rules for power, accountability & safety? Blockchain may be the answer.
Thread below👇