ayush retweeted
This level of formal verification was previously impossible, but now multi-agent systems can prove end to end security of software. We wrote and reviewed the specs to ensure correctness and human understandability; the agents proved the rest.
At Intrinsic, we apply AI to scale formal verification for software.
As a first result, we end-to-end formally verified @openvm_org, a production zero-knowledge proof system using @leanprover. Our verification shows OpenVM's cryptography is sound and matches its implementation.
ayush retweeted
AI is making cyberattacks far more dangerous, so at @axiom_xyz we formally verified @openvm_org to stay ahead of AI attackers.
Today we’re launching @Intrinsic_HQ to bring the same AI-powered provable security to the rest of software.
At Intrinsic, we apply AI to scale formal verification for software.
As a first result, we end-to-end formally verified @openvm_org, a production zero-knowledge proof system using @leanprover. Our verification shows OpenVM's cryptography is sound and matches its implementation.
ayush retweeted
At Intrinsic, we apply AI to scale formal verification for software.
As a first result, we end-to-end formally verified @openvm_org, a production zero-knowledge proof system using @leanprover. Our verification shows OpenVM's cryptography is sound and matches its implementation.
wonder how long before we go from formally verifying binaries to formally synthesizing them. who needs compilers anyway
New on our Frontier Red Team blog: using Claude to formally verify software at large scale.
Formal verification can prove that code is free of certain bugs, but historically it has only been feasible for small codebases (or required a lot of expert time).
With AI models, however, this is beginning to change. In collaboration with @theoremlabs, we used Claude to prove security properties in over one hundred real-world open-source libraries over the span of a few weeks.
Read our research in full here: anthropic.com/research/forma…
116
ayush retweeted
At @axiom_xyz we’ve been building RL environments to help AI models do FV at the binary level and accelerate defensive efforts like these. Our environments are based on real code, scalable, and challenge even frontier models. Get in touch if you are interested!
New on our Frontier Red Team blog: using Claude to formally verify software at large scale.
Formal verification can prove that code is free of certain bugs, but historically it has only been feasible for small codebases (or required a lot of expert time).
With AI models, however, this is beginning to change. In collaboration with @theoremlabs, we used Claude to prove security properties in over one hundred real-world open-source libraries over the span of a few weeks.
Read our research in full here: anthropic.com/research/forma…
We rewrote openvm execution (again!) and it’s ridiculously fast
More details in my blog:
shuklaayu.sh/blog/riscv-reco…
ayush retweeted
We are excited to release OpenVM 2.1 Preview, an early look at the performance of the next version of OpenVM.
It adds 64-bit RISC-V support, adopts a redesigned execution, and now proves mainnet Ethereum blocks in real time on only 4 5090 GPUs, a 2x improvement over OpenVM 2.0.
ayush retweeted
We're excited to announce the production release of OpenVM 2.0, featuring state-of-the-art performance and enterprise-ready security.
OpenVM 2.0 proves Ethereum in real time on 8 GPUs and is secured by a combination of human review, formal verification, and continuous AI audits.
ayush retweeted
We are announcing OpenVM 2.0.0, the first production release of OpenVM 2.0.
This release is externally audited with expanded formal verification and proves Ethereum mainnet in real time on as few as 8 GPUs. Proving times are down 95x since the first release 18 months ago.
Job’s not finished
Today we're releasing OpenVM 2.0 Beta, which proves Ethereum mainnet blocks in a p99 time of 7.9s on 16 GPUs and hits 964 MHz RISC-V throughput on 64 GPUs, making it the fastest zkVM on @eth_proofs.
Here's what's new and what's next:
2
494
ayush retweeted
A Trillion Transactions with TigerBeetle
Starting in 5 minutes!
youtube.com/watch?v=y2_BqkKT…
ayush retweeted
Excited to see a WASM zkVM built on @openvm_org.
Our vision for OpenVM has been to support a diverse set of ISA frontends on top of a uniform backend, and it's been impressive to see @powdr_labs prove the thesis by shipping WASM and even integrating Geth!
Announcing powdr-wasm!
powdr-wasm is an optimized zkVM for WASM, built on top of @openvm_org and the novel 𝑐𝑟𝑢𝑠ℎ ISA.
Early benchmarks already show 1.5x fewer trace cells & faster proof times compared to RISC-V (OpenVM).
It also supports Go guests via WASI!
👇
Cool to see openvm being extended like this. @powdr_labs folks crushing it!
Announcing powdr-wasm!
powdr-wasm is an optimized zkVM for WASM, built on top of @openvm_org and the novel 𝑐𝑟𝑢𝑠ℎ ISA.
Early benchmarks already show 1.5x fewer trace cells & faster proof times compared to RISC-V (OpenVM).
It also supports Go guests via WASI!
👇
2
251
ayush retweeted
The functional correctness of the OpenVM RV32IM extension has been formally verified using @leanprover by @Nethermind with support from @ethereumfndn.
This marks a major step in incorporating formal methods into OpenVM's development process that we will maintain going forward.
ayush retweeted
Our Formal Verification team led by @PetarMax, with support from @EthereumFndn, has verified in Lean the correctness of the OpenVM RISC-V extension built by @axiom_xyz.
This work proves instruction-level correctness and, for the first time, execution and memory consistency.
🧵
ayush retweeted
It was a great pleasure to lead the formal verification of OpenVM. This is the most complete FV effort to date of a real-world RISC-V zkVM.
Big thank you to @theyisun and @jonathanpwang from @axiom_xyz for their support in this process, and to @ethereumfndn for the funding.
Our Formal Verification team led by @PetarMax, with support from @EthereumFndn, has verified in Lean the correctness of the OpenVM RISC-V extension built by @axiom_xyz.
This work proves instruction-level correctness and, for the first time, execution and memory consistency.
🧵
ayush retweeted
We partnered with @Nethermind with support from @ethereumfndn to formally verify the functional correctness of the OpenVM RISC-V extension using @leanprover.
Alongside this, we are introducing provable 100-bit security on the Axiom Proving API with the new OpenVM 1.5.0 release.
ayush retweeted
We are excited to announce a collaboration with @Lighter_xyz to build Lighter EVM with ZK verification using @openvm_org.
Lighter EVM is an EVM-equivalent rollup which can natively access the liquidity of Lighter's perps and spot markets.
