AnecdoteArticle

LLMs tend to think it is impossible to solve cryptographic problems so they don't try; they need a good amount of prompting to persist.

The researchers found that Claude Mythos defaulted to giving up on hard cryptographic problems, requiring sustained prompting to keep working. ✦ AI generated

Anthropic researchers · Simon Willison's Weblog · 2026-07-28 · original ↗

Share card ↓Export .md Export .txt

the models tend to think it is impossible to solve so they don't try they need a good amount of prompting.

Read full article ↗excerpt · fair-use quotation

▦ Anthropic ✳ Claude Mythos

Around this claim

Mechanism · 1

LLMs have no true understanding — they are the most sophisticated pattern-matching autocomplete systems ever built, and their output is just statistical inference over text, not a replication of human intelligence.CJ · Syntax · conf 70%

Context · 1

Language has deep statistical structure, and an LLM is fundamentally doing the same thing Claude Shannon measured in 1950 — predicting what comes next given enough context.CJ · Syntax · conf 70%

This moment responds to

provides context → The goal is to have a highly intelligent model as good as a top human researcher, and use it to find new attacks — not to replicate existing approaches.Anthropic researchers · Simon Willison's Weblog provides context → The research should find something that is worth publishing — not low-hanging fruit, but genuinely hard findings.Anthropic researchers · Simon Willison's Weblog explains mechanism → Claude Mythos Preview worked for 60 hours total at an estimated API cost of ~$100,000, and the main human interventions were encouraging it not to give up and to find something worth publishing.article author · Simon Willison's Weblog