Cryptography Expert Tests: Frontier LLMs Struggle to Crack Classical Ciphers
matthew_d_green · x · 2026-07-20
Cryptography expert Matthew Green shared the results of a side project: he tested frontier large language models equipped with tools to crack various historical classical ciphers.
He found that while these models theoretically "know" a lot about cryptography, translating that into actual decryption operations is incredibly slow and challenging. Even top-tier coding agents without tool assistance often stall or give up entirely on such tasks, exposing current models' limitations in complex logical reasoning and long-horizon task execution.
Related event: Crypto Expert Tests LLM Decryption, Exposing AI Toolchain Flaws(13 posts)→
More from coding & agent
- A roundup of AI agents and MCP resources, including how to evaluate agents — _jaydeepkarale · 2026-07-21
- Anthropic shares a masterclass on how it builds AI agents — _jaydeepkarale · 2026-07-21
- Anthropic masterclass spotlights how to build and observe AI agents — _jaydeepkarale · 2026-07-21
- A beginner guide to AI agents points readers to a Stanford webinar — _jaydeepkarale · 2026-07-21
- A full course shows how to build and deploy an AI agent with OpenAI and LangChain — _jaydeepkarale · 2026-07-21
- A practical guide on how to evaluate AI agents — _jaydeepkarale · 2026-07-21