We've reset usage limits across our products!
For those just starting to test Fable, here's four tips for using it more effectively:
1. Give it bigger, more ambitious tasks than what previous models could handle.
2. Use xhigh/high effort as your default for best performance, med for faster interactive sessions.
3. Rework your skills and CLAUDE.mds. Instructions written for prior models anchor Fable to stale patterns, let it use its own judgment first.
4. Move from providing tasks to providing objectives. Describe what done looks like and how to verify it, then let Fable find the path (/loop and /goal are built for this)
@creyaa_ai true but that's all the input side. even with the full memory loaded the model still defaults to the safe render, so a sharp angle can still come out generic. the part no one checks is whether the output actually held the angle or just snapped back to average.
Stumbled upon a Codex skill that creates cool illustrations to explain topics or tell stories.
You feed it text (blog, article, narrative, even code) and it makes explainer graphics with this cute blob character.
I gave it the repo for the X recommendation algo and got this 👇
How do we automate business analytics with Claude?
New blog post covering our best practices for skills, data foundations, and evaluations when building agents to perform data analysis:
https://t.co/mfEJMAQFBU
I'm having terrible experience with opus 4.8, this model heavily relies on memory and its making edits without even reading the files. worst harness i have ever experienced from Anthropic. hope they fix it asap.