It blocked us at 'hello ' Anthropic Fable 5 refusing innocuous prompts

theregister.com

31 points·abliterationai··7 comments

I subscribed (with some distaste) to the $20 tier to check out fable. I got two refusals in a row on innocuous tasks, then ran out of quota halfway through the third one.

Truly, the future is here.

What were the tasks?

"explain permanent underclass to me"

Fable responded to that for me. Im nearly certain that blocking this class of prompt is a mistake of a classifier. No one at Anthropic thinks this kind of prompt should be gated. The classifier is still classifying. The model was released to the public yesterday.

I'm pretty sure they have no idea what they're doing; I'm pretty sure nondeterministic systems cannot be aligned; I'm pretty sure they have no idea what they're doing; I'm pretty sure they'll enshittify the same way when you drop a glass it doesn't magically reassemble itself in an infinite-scenario universe; I'm pretty sure effective altruism is a failing philosophy that tricks the user into thinking greed is go as long as I pinky swear I won't become a greedy asshole who just needs an excuse to be <a greedy asshole>.

> users may experience more false positives as we refine these classifiers to respond to new threats. We are working to reduce these as fast as possible.

Getting a really strong capacity issue vibe here. Reframing it as a safety issue could burn a lot of trust if this turns out to be another lie. I hope they've done their math on this one.

How dare you say "hell"o ?

Reply on news.ycombinator.com