An engineer shared how Anthropic's Fable 5 began outlining a Python decorator solution during routine coding help before its internal classifiers cut the thread with an API error, highlighting the model's new conservative safety layer in action.
"hey fable how could we do X" - "yeah so we can do a small python decorator here, this is how it will look like. should i implement it?" "oh yeah, lets do that"
⏺ API Error: Fable 5's safeguards flagged this message
lmao, oh well
The model launched with separate classifiers tuned to block potential misuse in areas like cybersecurity, which sometimes activate on harmless prompts and force fallbacks or errors.
Developers responded with jokes about switching to other models or satirical commands rather than any confirmed bypass methods for the flagged sessions.
Many users criticized Fable 5 safeguards for blocking routine Python coding requests due to slow performance, high costs versus output quality, and overly restrictive behavior.
No Digg Deeper questions have been answered for this story yet.
i feel very safe
the irony is that you can always prompt your way around those, its not even hard, just annoying.
back to gpt and glm, fable is a plan md generator
"hey fable how could we do X" - "yeah so we can do a small python decorator here, this is how it will look like. should i implement it?" "oh yeah, lets do that"
⏺ API Error: Fable 5's safeguards flagged this message
lmao, oh well
@xeophon you can fix that by running below in a new terminal window:
codex -m gpt 5.5
"hey fable how could we do X" - "yeah so we can do a small python decorator here, this is how it will look like. should i implement it?" "oh yeah, lets do that"
⏺ API Error: Fable 5's safeguards flagged this message
lmao, oh well
@dejavucoder @xeophon
@reach_vb @xeophon you cheeky bastards
@reach_vb @xeophon gpt 5.6 wen sir
@reach_vb @xeophon gpt-5.5 has to be a typo, should be gpt-5.6-sol 😄😉
@reach_vb @xeophon Vaibhav Sol wen?
@reach_vb @dejavucoder @xeophon i dont like chairs
@kylecompute Yes
@xeophon
@reach_vb @xeophon yeh but where gpt 5.6?? fable high is better than XHIGH :(
@xeophon I want to try Fable 5 but still haven’t because it sounds like it would be a return to interrupted workflows
@reach_vb @xeophon Sol pewnie jak fable wyleci z subskrybcji.
@xeophon Honestly I find fable too expensive for the quality of code it generates anyway. I much prefer to use it as an architect, and find that I get less refusals this way. That said, thank you president trump for even more refusals with this release.
@xeophon Have been thinking abt trying glm5.2 lately
Have liked minimaxm2 and 5.1 was good at cua but not sure how new 5.2 is
Good daily driver?
@xeophon I got a repro that hits that safeguard with the prompt "hi"
@xeophon Ye python usage is a serious mental health risk
@reach_vb @xeophon 5.5 xhigh is slow as molasses though
@reach_vb @xeophon codex -m gpt 5.6-sol will be better right?
@xeophon A Good Plan Is All You Need