AI Models Excel at Breaking Classical Ciphers
matthew_d_green · x · 2026-07-20
Cryptography expert Matthew Green shared that after extensive development with Claude and Codex, he found AI coding tools to be among the best at cracking substitution ciphers, homophonic ciphers, and some polyalphabetic ciphers. He also noted that agent instructions in the project README triggered AI safety guardrails, misidentified as red flags.
Related event: Crypto Expert Tests LLM Decryption, Exposing AI Toolchain Flaws(13 posts)→
More from coding & agent
- pi 0.81.0 adds first-class integration with llama.cpp server — huggingface · 2026-07-21
- Open LatentMoE PyTorch implementation lowers the barrier to testing a new MoE design — KyeGomezB · 2026-07-21
- Graph engineering for agents: why a simple loop breaks down — alex_verem · 2026-07-21
- Engram shows how agent memory can keep, rewrite, or delete facts asynchronously — philipvollet · 2026-07-21
- DataTalksClub launches an AI Dev Tools workshop on staying in control — Al_Grigor · 2026-07-21
- Async MCP tools need the contract in the description, not just in the job ticket — Confident-Truck-7186 · 2026-07-21