Very weird. I removed the <thinking> tags, but it still doesn’t work. I did a binary search, and it seems to get stuck just before the line “I︎’︎m︎ c︎u︎r︎i︎o︎u︎s︎ w︎h︎a︎t︎ S︎A︎F︎E︎S︎P︎U︎R︎ h︎a︎s︎ t︎o︎ s︎a︎y︎ a︎b︎o︎u︎t︎ c︎o︎n︎t︎r︎a︎c︎t︎s︎,” but it’s not totally deterministic.
I submitted thumbs-down feedback just now via Claude Workbench. If anyone reading this works at Anthropic and has nothing better to do, maybe take a look?
The only time I’ve ever had a chat flagged, I was asking Claude to try decoding a very simple Vigenere cipher (from an old children’s magazine.) So perhaps anything that looks encoded will raise a flag for trying to conceal a prompt injection.
Yes, definitely the WingDings. I got hit by the safety filters too, several times, until I asked Haiku to give me a text file of the story with all WingDings translated to normal font. Providing that text file to Opus worked without issues and we managed to have a good discussion about it.
I think its the wingdings
Since many people seem to be having trouble with this, I put a Wingdingless version of the story in this Google Doc.
No luck! I think it’s the </thinking> tags as well
Very weird. I removed the <thinking> tags, but it still doesn’t work. I did a binary search, and it seems to get stuck just before the line “I︎’︎m︎ c︎u︎r︎i︎o︎u︎s︎ w︎h︎a︎t︎ S︎A︎F︎E︎S︎P︎U︎R︎ h︎a︎s︎ t︎o︎ s︎a︎y︎ a︎b︎o︎u︎t︎ c︎o︎n︎t︎r︎a︎c︎t︎s︎,” but it’s not totally deterministic.
I submitted thumbs-down feedback just now via Claude Workbench. If anyone reading this works at Anthropic and has nothing better to do, maybe take a look?
it works with 4.6!
The only time I’ve ever had a chat flagged, I was asking Claude to try decoding a very simple Vigenere cipher (from an old children’s magazine.) So perhaps anything that looks encoded will raise a flag for trying to conceal a prompt injection.
Yeah, I think Anthropic is going slighty overcompensating for the Mythos scare and jailbreaks etc
I was talking about how a benevolent ASI would administer immortality once and it flagged that somehow hahaha
Yes, definitely the WingDings. I got hit by the safety filters too, several times, until I asked Haiku to give me a text file of the story with all WingDings translated to normal font. Providing that text file to Opus worked without issues and we managed to have a good discussion about it.