i fear i've spent a month making something that already exists.
a workflow lazily titled 'mission control'. one chat that knows my work, opens other threads on specific models and efforts. they do the job, report back, close out.
then i got into the early beta of claude duet,
in the midst of this really long build i learn about @theo, and then @t3dotcodes, and it seems like a lot of what i've been building, he might have already built.
trying it out today. excited to see how it works. t3 users, tell me how it’s changed things for you, please.
and although it was wayyy prettier, it didn't work better. kept ending up back on terminal w/ @claudeai
recently i decided to add some code to it, give it more structure etc. that turned into an insanely ambitious build. like tens of thousands of lines of code.
sometimes im like, is the model nerfed... or is my work getting harder and i need to level up my workflow.
fable 5.2 has helped me reach the shortcomings of opus 5.5, and also helped me level up how i use these tools.
incredible work @AnthropicAI@claudeai
they realized no one was using fable 5.1 once opus 5.5 dropped and this plus resets is how they get us back into the fable fold.
anthropic has a great lineup. every model is valuable and fits snug in a workflow. i actually use them all.
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges.
They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
why do people think they’re being routed to new models like fable 5.5 or sol 6.2 but say they’re ‘nerfed’ instead of them being routed to an unreleased weaker model?
you’re being routed to haiku 5.5 😂 congratulations.🎉
@FroodyBanana@voidfreud imagine coding something and the app does something broken, and someone says, “ahh show me the code” and you say “that defeats the purpose” 😂 this is dumb.