Trustless Agents — with zkML
Ethproof's quest to verify Ethereum blocks in real-time can also be leveraged in a similar race for near real-time verifiable compute for trustless agents — here's how.
Wyatt Benno
Sumcheck good. Lookups good. JOLT good. Particularly for zero-knowledge machine learning.
TL;DR: We made zkML 3-7x faster than everyone else. Here's how.
Standing on the shoulders of giants
The a16z crypto research team recently dropped some serious heat with their 6x speedup announcement, showing how JOLT's lookup-based approach with sumcheck protocol can dramatically outperform other SNARK
Verifiable AI Memory — When AI Remembers, Who Controls the Truth?
The future arrived, and it tastes like corporate surveillance.
AI can now remember a lot about you. Not just your conversation from five minutes ago, but you — your preferences, your quirks, the embarrassing thing you asked about cryptocurrency in March. AI memory is not only a blossoming set of features,
Verifiable AI: Moving From a Black Box To a Glass House.
▓▓▓▓▓▓▓▓▓▓▓ ░░░░░░░░░░░
▓ ▓ ░ ░ ░
▓ ? ▓ ░ P ░ R ░
▓ ▓ ░ ░ ░
▓ ▓ ░░░░░░░░░░░
▓ ▓ ░ O ░ O ░
▓ ▓ ░ ░ ░
▓ ▓ ░░░░░░░░░░░
Succinct Verification, The Key to AI.
It may seem presumptuous for someone steeped in cryptographic proof systems to claim insight into the future of AI. After all, if there’s a better path forward, why not just build it and let the results speak for themselves?
Fair. But some problems are structural — and it’s precisely
If A 'ZK'-Prover Network Asks For Your Data. Don’t Give It to Them.
When many users hear the term zero-knowledge proofs (ZKPs), they assume privacy is built-in by default. After all, “zero-knowledge” sounds like it means “no one knows my data,” right?
Wrong.
In reality, many ZK prover networks don’t care about privacy at all — they care about speed. The dominant model
Pick, Prove, Profit: The NIVC Singularity.
Incrementally Verifiable Computation (IVC) was first introduced by Valiant in his seminal 2008 work. This groundbreaking concept enables recursive proof systems to tackle long proving tasks by breaking them down into incremental steps. While transformative, the original implementations relied on a universal circuit, meaning the same circuit was repeatedly proven
zkGPU - On the State of the Art for Verifiable Compute of GPU Execution.
*This post is about verifying the computations run on GPU. Not using GPUs to accelerate ZKP!
GPUs are having a long — moment in the spotlight. Often celebrated for their prowess in rendering lifelike graphics, GPUs now sit at the heart of some of the most demanding computational tasks in modern
Minimal Space, Maximum Pace: How memory efficient zero-knowledge proofs work
In the rapidly evolving world of blockchain and cryptography, we often hear about blazing-fast zero-knowledge virtual machines (zkVMs) designed to scale Ethereum or tackle large-scale computational problems. However, for true privacy, ZKPs need to run locally. This concept, known as local verifiable compute, involves implementing extremely space-efficient ZKPs for use
Proof Composition Using Zero-Knowledge Virtual Machines: #RunawayZK
Zero-knowledge proof (ZKP) systems often require composition with other ZKP systems to achieve specific traits, such as privacy or improved on-chain verification (e.g., Groth16). Traditionally, this process involves cryptographic experts meticulously converting the verifier of one system into an arithmetic circuit for use in another. This labor-intensive task is