Ex-smart contract auditor (4+ years) advancing blockchain security via machine learning. Currently mastering linear algebra and matrix operations to build AI-na

Security to ML
Joined December 2009
I guess Jev can also be very useful in web3 security agents, as well as onchain guards!
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
4
985
Glad you liked the smart contract vulnerability dataset. In my open-source project LazyAuditor, I’m experimenting with compressing smart contracts by up to 60% without losing their meaning. This can be especially useful for AI agents. Here’s how it works: ⤵️
1
1
24
1,404
Why does this matter? The smaller the code, the fewer tokens the LLM needs to analyze it. This lets you fit more Solidity code into a single request and reduce audit costs
1
2
110
23 625 smart contract vulnerabilities — open sourced I collected these findings over the past year from private audit reports and contest platforms Hopefully, it’ll be useful for security researchers and people working on AI for smart contract security huggingface.co/datasets/Zaev…
13
41
5
279
16,670
The dataset is still in its raw form and needs some cleaning/normalization before it’s ready for ML training. Also available on GitHub — a ⭐️ would be appreciated! github.com/zaevlad/lazyaudit…
2
19
1,425
It comes with limits reset!
Fable 5.1 is now live in Claude Code and the Claude Platform. It's priced the same as Fable 5, with 75% cheaper API cache reads. It gets a lot further into a long task before it needs your input, is better at telling you when it's stuck, and its writing style is more natural.
471
Replying to @OpenRouter
@OpenRouter has done more for the crypto community than most modern projects, simply by allowing their users to pay with crypto. More platforms should enable crypto payments too. Tag companies in the comments that should offer crypto payments to their users I'll start 🔻
2
1
327
I'd like to see @ollama accept crypto payments
47
The main problem with GPT models is that the team focuses more on creating temporary hype in X than on making its models truly excellent. 1. Even after the latest release, it could not beat Claude in any category on LMARENA.
1
1
810
2. Users are trying to integrate Sol into Claude Code CLI because it's still better than Codex for developers. 3. Users also create workflows where Fable orchestrates Sol, but not vice versa. 4. Moreover GPT models still super lazy to follow long instructions.
1
216
Huge update to the VulnFlow Audit AI system 🎉 The chat is no longer just a text assistant. It now acts as a workspace-aware audit agent with access to files, RAG docs, pipeline state, external tools and live UI context. github.com/zaevlad/vulnflow-…
1
5
329
Visualization support was heavily expanded. The agent can generate interactive HTML/SVG widgets inside sandboxed iframes, attach follow-up prompts and build dynamic visualizations directly inside the chat interface.
1
49
Also added a Monaco-based editor integrated with the agent. Responses containing path:line references are clickable, opening the exact workspace file and scrolling directly to the referenced code location.
35
VulnFlow is built on local-first principles. 1. You don't need Claude Opus or ChatGPT-5.4 to write a simple vulnerability report. 2. Sensitive information should stay confidential.
1
1
327
Privacy by design: with local inference, all data stays on your machine. No external API calls. No data leakage risks. Critical when auditing confidential projects under NDA.
1
44