Anthropic has abruptly disabled its newly launched Claude Fable 5 and Mythos 5 AI models for all customers to comply with an urgent export control directive from the U.S. government today.
And Anthropic cannot selectively block foreign nationals while keeping the system open, they had no choice but to take both models entirely offline worldwide.
Will we see a time in the future when Local LLM’s get the crypto export ban treatment
Good, good, the message is loud and clear: the US can and will stop any service by any company to any country without prior notice or even consultation with anyone and with zero thought given to the long-term repercussions. Every country is seen as competitor at best, enemy at worst. If you depend on any inputs from the US in any form, this will be noted as potential leverage to be used when opportune.
Worth pointing out the OAI is US based too. And Mechahitler. And Google. All at the whims of US govt
Use em if you must (the OAI honeymoon deal - with generous Codex use being included on basic subscription - is hard to beat) but remember…the cloud is someone elses computer…and you especially don’t want mission critical shit on someone elses AMERICAN computer.
OpenCode is probably the best serious cloud competition to the big 4. $10 month.
Latest versions of GLM, MiMO, Deepseek, Kimi ain’t nothing to sneeze at
https://thomas-wiegold.com/blog/opencode-go-review/
If someone knows better cloud deal, speak up. Else, local Qwen uber alles.
US: Let’s not give an edge to China!
China develops its own tools
US: >_<
Oh, that’s weird. My Qwen seems to work just fine 😇
Kidding aside, I actually had a job I started with Fable the other day - specifically renewed so that I could use it.
Guess Opus will have to finish it and then I revert to free.
Truth be told, Fable was nerfed anyway with security theatre.
Good opportunity for ZAI or someone else to gain some ground.
No loyalty to cloud shit. They’re all cooked. Use what works.
So…is this Trump getting back at Darius for refusing to build autonomous weapons? I didn’t think he had the attention span.
Yes, they found a bullshit hidden test that other models also pass.
OpenAI didn’t get blocked. But they are letting the Trump admin build the surveillance state ABS weapons with their models.
Hah, they overdid their marketing and are reaping the rewards.
Its a win for anthropic, they don’t have to run the expensive model, but they’ve already taken everyone’s money.
(I have no idea if they are giving refunds, but I’d assume not)
They are. But the reputational cost? Who knows.
Edit: just got an email
Hello,
We recently removed access to Claude Fable 5 to ensure compliance with a recent US government directive. Here’s a summary of what’s happened:
You no longer have access to Claude Fable 5 You still have access to all other Opus, Sonnet, and Haiku models We reset your usage limits If this change doesn’t work for how you use Claude, you can cancel your subscription and get an automatic prorated refund.* To do so, visit this link from a web browser and click “Cancel plan” by Saturday, June 20, 2026, at 11:59 PM PDT (UTC−7). Note that this link will not work in the Claude mobile app. If you subscribed through Apple, please request your refund directly through Apple’s refund support.
We apologize for the disruption. You can learn more about Anthropic’s response and what led to this decision.
- Refunds are only available to eligible people who purchased a plan or upgraded their plan between 10:00 AM PDT on June 9, 2026, and 12:00 AM PDT on June 14, 2026 (UTC−7).
Claude Instagram LinkedIn X Youtube
Anthropic PBC, 548 Market St, PMB 90375, San Francisco, CA 94104
That’s a very short-term win, if so, with a long-term cost. Now anyone who’s thinking of spending money on an Anthropic subscription (or any other big American company for that matter) needs to consider the possibility that the product they get will be “too good” and therefore will suddenly get yoinked out from under them by the US government.
That long-term impact will be very beneficial for the local and open models because they can’t be taken away like that.
True, but are these AI companies concerned about the long term? They are both planning to IPO soon, so pumping the short term may be all they care about.
I don’t really care what they’re concerned about, I’m personally a long-term thinker on this.
