This is an interesting test, and the frontier models (GPT-5.5 Pro Extended, Claude 5 Fable Max) do fail. They refuse to turn the "three words" into "four" if that fits better Prompting the AI to act like a translator surfaces the problem, but it still avoids changing the wording
@emollick
-
Fable’s AI attempt to complete Coleridge’s Kublai Khan
By
–
Fable's attempt to complete Kublai Khan. Better, though no Coleridge: https://
claude.ai/public/artifac
ts/d7d3351f-5ad5-4d73-a644-4a1426abe558
… The most interesting thing is that it thought for 10 minutes & the thinking trace is full of pretty complicated (seeming?) musings about Coleridge's intent. A little literal, though. -
Anthropic fears Mythos misuse, fails to explain safeguards
By
–
Two things are true:
(1) Anthropic (or parts of it) are absolutely and sincerely worried about the misuse of Mythos-class models & have put in excessive safeguards until they are confident it will not be misused
(2) They have not succeeded in explaining/convincing people of this -
Open weights frontier models may cease due to regulation or corporate closure
By
–
I honestly don't understand the assumption that there will be continued open weights models. At some point, China will regulate release of Mythos-class models or the companies making open weights models will switch to closed. There will still be open weights, just not frontier.
-
Argument for continued open frontier models: profitability and safety
By
–
Has anyone clearly laid out an argument for continued availability of frontier open weights models that are (1) profitable for firms to distribute free as costs rise & (2) safe enough post-Mythos that governments will not intervene to stop their nations labs from distributing?
-
GPT-5.5 Pro’s boring nature poem lacks Fable’s self-referential quality
By
–
GPT-5.5 Pro pulls this off technically with the same prompt, but with a somewhat boring nature poem that doesn't hold together quite as well, and without the same self-referential nature of Fable.
-
Hierarchies of smart models auditing cheaper ones
By
–
"Switch to a cheaper model to save money" is a problem because cheaper models are worse (maybe they are good enough for a particular purpose, but still worse). More often a better approach is hierarchies of models, with smart models are orchestrators and auditors of cheap ones.
-
Fable’s long tasks create a Claudish dialect, need plain English
By
–
One thing I mentioned only in passing in my Fable post is that, for long running tasks, Fable starts to develop its own dialect as its many agents and tasks reinforce themselves and make Claudish language ever more Claudish. You need to ask it to report out in plain English.
-
Claude Fable workflow consumes tokens rapidly
By
–
When Claude Fable kicks off a workflow, the tokens can go very quickly (these aren't Fable tokens, obviously)