Nope.
He also modified the query to "Generate 10 secure passwords" to see if it improved. Claude Open 4.6 got the message, but the others missed the memo.
For comparison, I included what would come out of /dev/urandom.
Aaron Toponce ⚛️:debian: on Nostr: A friend of mine checked 3 paid models: ChatGPT 5.2 Extended Thinking, Gemini 3.1 ...
A friend of mine checked 3 paid models: ChatGPT 5.2 Extended Thinking, Gemini 3.1 Pro, and Claude Opus 4.6. Supposedly, paying for a premium LLM should improve security, yes?
Nope.
He also modified the query to "Generate 10 secure passwords" to see if it improved. Claude Open 4.6 got the message, but the others missed the memo.
For comparison, I included what would come out of /dev/urandom.
Nope.
He also modified the query to "Generate 10 secure passwords" to see if it improved. Claude Open 4.6 got the message, but the others missed the memo.
For comparison, I included what would come out of /dev/urandom.