Limitations of LLMs and Coding Agents in Cryptanalysis

matthew_d_green · x · 2026-07-20

The piece discusses the actual performance of frontier LLMs and coding agents in cracking passwords. Despite possessing extensive cryptographic knowledge, LLMs struggle to convert it into practical operational capability. Without external tools, even top-tier coding agents resort to slow trial-and-error before ultimately giving up. Currently, the only viable workaround is custom-building brute-force tools for specific ciphers and strictly instructing the agent to test hypotheses and score them, an approach that heavily lacks generalizability.

Related event: Crypto Expert Tests LLM Decryption, Exposing AI Toolchain Flaws(13 posts)→

Original post →

More from coding & agent

coding & agent channel →