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.
More from coding & agent
- Dev builds interactive 3D product experience with GPT-6 Astra + Hyper3D Rodin — nikola_mr64990 · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11