Wednesday, 10th June 2026
If Claude Fable stops helping you, you’ll never know (via) Jonathon Ready highlights one of the more eyebrow-raising details from the 319 page system card for Fable 5 and Mythos 5. Here's a longer excerpt, highlights mine:
In light of the ability of recent models to accelerate their own development, we’ve implemented new interventions that limit Claude’s effectiveness for requests targeting frontier LLM development (for example, on building pretraining pipelines, distributed training infrastructure, or ML accelerator design). Using Claude to develop competing models already violates our Terms of Service, but enforcing this restriction through our safeguards avoids accelerating the actors most willing to violate these terms.
Unlike our interventions for cybersecurity, biology and chemistry, and distillation attempts, these safeguards will not be visible to the user. Fable 5 will not fall back to a different model. Instead, the safeguards will limit effectiveness through methods such as prompt modification, steering vectors, or parameter-efficient fine-tuning (PEFT). These interventions will not affect the vast majority of coding work. We estimate they will impact ~0.03% of traffic, concentrated in fewer than 0.1% of organizations.
I believe this is the first time Anthropic have announced these kinds of silent interventions. The justification still feels pretty science-fiction to me - the linked article talks about "recursive self-improvement". I'm not at all keen on a model that silently corrupts its replies to questions about "ML accelerator design" purely to slow down research that might conflict with Anthropic's own goals!
Update: Anthropic walked back this policy in the face of widespread outrage from the research community.
Easy solution to slow down recursive AI self improvement:
- The lab with the top-ranked model must agree THEY must not use it for working on frontier AI
- But everyone else should have access to it.
By definition, this means the frontier doesn't advance.
It also has the critical benefit of avoiding a dangerous power imbalance.
Anthropic has chosen the opposite of the safe path: they are allowing themselves, the current top lab, to use their top model for frontier AI research. They've said they'll sabotage others who try.
This means the AI frontier advances, & power imbalance increases.
(To be clear, I don't think we should try to slow down recursive AI self improvement - I think we should open it up and democratize it as much as possible. My point is: if you claim we should slow down, and you have the best model, you should ensure your org can't use it.)
— Jeremy Howard, in a Twitter thread
DiffusionGemma (via) Last May Google briefly released an experimental Gemini Diffusion model. I tried the preview at the time and recorded it running at 857 tokens/second. It was an exciting model, but Google made no further announcements about it.
That research has returned in the best possible way: as a new open weight (Apache 2 licensed) Gemma model, google/diffusiongemma-26B-A4B-it.
NVIDIA are currently hosting the model for free on their NIM cloud API. I used that API to generate this pelican, which took 4.4s (according to time uv run generate.py) to return 2,409 tokens - so at least 500 tokens/second.
Highlights from the release notes:
- Tools can now ask the user questions mid-execution. Tools that declare a
contextparameter receive aToolContextobject, andawait context.ask_user(...)can ask a yes/no, multiple-choice (options=[...]) or free-text (free_text=True) question. While a question is unanswered the agent turn suspends: the question renders as a form in the chat UI and persists to the internal database, so suspended conversations survive a server restart. Once answered, the tool re-executes from the top with stored answers replayed, so callask_user()before performing side effects. #20- New built-in
save_querytool: the agent can save SQL it has written as a Datasette stored query. Saving always requires human approval - the agent shows the full SQL plus the proposed name, database and visibility, and nothing is stored until you click Yes. #20
The ask_user() feature was enabled by the new LLM alpha I built yesterday with the help of Claude Fable 5.