[__natty__]

This makes Fable unusable for me. If I cannot tell whether I am paying for the whole service or just a partial one, because somehow their guardrails have decided my work silently broke their terms of service, then I prefer to go to older models or alternatives

[maxall4]

As someone who works in bioinformatics, and, as such, does a great deal of machine learning, this makes Fable unusable for me as well.

[flexagoon]

Fable would be unusable for you in a more literal way, since it just directly refuses to answer any query even remotely related to biology

[maxall4]

I’m very aware of this as well.

[hedora]

How do local models work? I’m specifically interested in things that run in the 32-128GiB space. (I don’t care about bio specifically; just trying to track when local models start surpassing cloud ones in some practical dimensions).

[ekidd]

At different size ranges:

- Qwen3.6 27B runs quite nicely on a 32GB GPU, and it's a mostly usable coding agent. The biggest difference with a frontier model is that a 27B forces you work in chunks between 100-200k tokens, and to maintain a clear understanding of how your code works. If you try to vibecode without understanding, yeah, it's going to get ugly. Also, it's better at coding than many other tasks.

- DeepSeek V4 Flash is apparently quite nice if happen to have 256GB of RAM lying around, lol. Again, not a frontier model, but antirez really likes it.

[ivanmontillam]

For sure Anthropic should be developing a model without these guardrails for your use case? Kinda like Mythos is only available to certain organizations.

[sterlind]

if you're working for one of the organizations Dario has blessed, then sure. you're SOL if you're not one of the top-3 whatevers. maybe they'll let MIT, Harvard and Stanford use Mythos for biology. good luck to everyone else!

[varispeed]

I am sure they've been doing that with Opus. I am getting mixed results all the time.