/Tech22h ago

Anthropic resets usage limits for its new Fable model, advising developers to use broader prompts and higher effort

Legacy CLAUDE.md instructions can restrict the model's judgment.

2023.1K1691.7K384.8K
Chubby♨️
Alex Volkov
Alex Albert#442
Original post
Alex Albert@alexalbert__#442inTech

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)

3:00 PM · Jun 9, 2026 · 359.6K Views
Sentiment

Positive users thank Anthropic for resetting Fable 5 usage limits because it relieves immediate caps, while negative users criticize the model's guardrails that block medical and biotech queries.

Pos
67.8%
Neg
32.2%
65 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS23.6KBOOKMARKS13LIKES196RETWEETS5
Chubby♨️@kimmonismus

yay weekly reset, thanks!

Alex Albert@alexalbert__

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)

21hViews 23.6KLikes 196Bookmarks 13
REPLIES5
Alex Volkov@altryne

Lol this is my (MAX) usage post reset, on one dynamic workflow. 😅

Alex Albert@alexalbert__

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)

21hViews 2.1KLikes 8Bookmarks 1
Rich Kuo@richkuo7

@alexalbert__ ohhh nice ty, i was at 99% and was like, what am i gonna do for the next 4 hours and 30 minutes lol

22hViews 889Likes 7
13yr old with a credit card@13yroldwithcc

@alexalbert__ Can you give examples of how to use Fable? Every time it reads `unsafe {}` in my Rust code it defaults to Opus 4.8. It won't even chat to me it immediately disengages

21hViews 118Likes 3
The Opinionated Human@TheOpinionatedH

@alexalbert__ Please keep it in subscriptions after June 22nd. It's cheaper than Opus 4...

21hViews 94Likes 2
Self Aware Networks 🇺🇸 🇹🇼 🇺🇦@worksalt

I'm not impressed with what Fable / Mythos has done so far today before I hit the 5 hour limit. I guess I only get about 5 tries per week since 20% of my weekly has already been consumed. I just ran one chat with a goal that outlined a large project, and it repeated a ton of the same types of errors that Codex 5.5 performed. I didn't make any real progress on my project.

17hViews 174Likes 2
Alex Albert@alexalbert__

@richkuo7 🙌

22hViews 747Likes 3
Prithvish ⋅ d4mr@earth_ish

I am beyond impressed by its capabilities (as is everyone else). but using it is proving impossible because of the guardrails. especially because of the kind of product I am using it to build, even the most benign prompts are getting rejected.

please fix the safeguards before the model is removed from subscription

21hViews 164
Kenny Lamoot@kennylamoot

@wxrrjxr @alexalbert__ Rarely get near it. Subagents plus /clear, and I ask the model to write the handoff prompt for the next fresh session.

21hViews 25Likes 1
Petio Lazarov@petiosz

@alexalbert__ Okay but what about the bug where it just treats everybody as a criminal and wont do basic every day tasks, because it thinks they are unethical??

22hViews 518Likes 2
Smelter Labs AI@SmelterLabsai

@richkuo7 @alexalbert__ And then 23 minutes later, you were at 99% again. Lol. Same for me.

17hViews 12Likes 1
King of Bitchain@KingOfBitchain

@alexalbert__ @AndrewCurran_ Nice! Love it so far. Solid model. Managed to avoid censorship speed bumps up to now.

18hViews 11Likes 1
Wxrrjxr@wxrrjxr

@kennylamoot @alexalbert__ How does ur cable even do anything useful to get to 400k 😂😂

Every damn engineering prompt is blocked

21hViews 34
calum dew@calumjdew

@alexalbert__ After running Fable for 16 minutes i maxed my current usage window and used 21% of my total monthly sub with zero results... wth

21hViews 27
John Helmuth@johnhelmuth_

@alexalbert__ @AndrewCurran_ What are your recommendations on how to adjust Claude.md and skills most effectively?

I guess I shouldn’t actually do this anyway because as of June 23 I’ll need to tweak them right back 😩

19hViews 207Likes 2
Dr Argy Bargy ⛩️@DrArgyBargy

@alexalbert__ I feel like the rate limits might need some adjustment. This ran out pretty fast.

21hViews 178Likes 2
Marius Miclau@MiclauMarius

@alexalbert__ did that , now what do I do ? 😀

I think I'm going to sleep

19hViews 162Likes 2
Kenny Lamoot@kennylamoot

@wxrrjxr @alexalbert__ Not yet. But my work is product code, refactors, agent orchestration, nothing security-adjacent.

21hViews 3Likes 1
Justin@JustinPerea

@alexalbert__ I don't want to remove my Claude md for my other models. Can you set a global Claude Md just for Fable?

21hViews 314Likes 1
Beat Poet@UrbanEcholot

@alexalbert__ I hit my usage limit after just two prompts and in both cases, Claude Fable refused to answer for safety reasons, even though the prompts were about a fictional story.

14hViews 8
Load more posts