Menu

Post image 1
Post image 2
1 / 2
0

I built a cryptographic audit receipt for Claude Mythos (and any AI model) — here's how it works

DEV Community: rust·Pulkit Srivastava·3 days ago
#9pXLdtgB
#dev#aetherproof#receipt#python#model#hash
Reading 0:00
15s threshold

Anthropic's Mythos model can autonomously find zero-day vulnerabilities. Their CVD disclosure process uses manual SHA-3-512 hash commitments to prove findings existed. I built something that automates that in one line of Python. What AetherProof does One function call generates a 128-byte Ed25519-signed receipt that proves: What model ran — FNV-1a hash of provider/model ID What it produced — hash of the output When — cryptographic nanosecond timestamp Tamper-evident — flip any byte anywhere → INVALID python import aetherproof receipt = aetherproof.for_anthropic( "Find vulnerabilities in this binary.", finding_text, model="claude-mythos-preview" ) receipt.save("CVE-2026-001.receipt") print(receipt.verify()) # True Try it in 30 seconds pip install aetherproof python -c " import aetherproof r = aetherproof.for_anthropic('question', 'answer') print(r.verify()) # True print(r.pretty()) " The unusual part — invisible Unicode watermarking Receipts embed invisibly into any text using Unicode Private Use Area…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.

Read More