Hacker News Reader

Comment by markbao | Hacker News Reader

[flagged]

I wanted to use Fable to discuss a philosophical topic, but halfway through I used the word "cell" and got deflected to Opus.

On the other hand Opus has this awful adversarial-teacher vibe. It pushes back for no useful reason, talks down to you, and acts like it has to prove itself by grading and correcting everything. Instead of working with your claim, it reframes it, declares what the "real" issue is, then tells you what you failed to do.

So Fable refuses me and I can't stand Opus. Nice one, Anthropic, I need to downgrade my subscription.

the title was flamebait, but its true for him...and for me. I do neuroimaging. It won't answer any question / coding task having to do with data analysis / statistical analysis. etc. It IS useless, for me.

there's plenty of uses for models not doing what they were made to do, but this is even worse. It's people trying to get the model to do what it was made specifically not to do!

You are mischaracterizing what the post is reporting entirely. Porting an open source tool used in bioscience to rust is a software engineering task. But it is somewhat understandable that it gets stuck in the overly broad safety margin.

But I do research on stuff that is entirely unrelated to bio or cybersecurity, and the model is simply not taking any of my research-level prompts. This is fairly abstract mathematical stuff. All of this, including all the examples in the posted article, are far from "trying to get the model to do what it was made not to do".

We don't need top-end frontier models to write simple applications. Opus works very well for that and it's cheaper. We need them to write things that are at the frontier.

We need? Do we?

I havent used fable, but does it cost you the same when it downgrades to opus?

I believe they confirmed, on twitter or somewhere I frustratingly can't find, that downgrades are charged at the correct opus rate, after a user asked and was told "either that's how it works or it's a bug"

With the subscription, it costs less to use opus in that it doesn't chew up our session however the cost/benefit is balanced against not performing as well on certain tasks. So it's not a straight up yes/no.

I don't think they charge if you downgrade, but if you upgrade from opus to fable they will charge you.

> the very thing Anthropic says it's not good for

Where? Certainly not in its announcement, for one: https://platform.claude.com/docs/en/about-claude/models/intr...

No "don't use this for X".

I thought it was the very first line of the product announcement, where they defined what it was they were calling "Fable" as opposed to "Mythos" in the first place:

https://www.anthropic.com/news/claude-fable-5-mythos-5

> Today we’re launching Claude Fable 5: a Mythos-class model that we’ve made safe for general use.

It then goes on to a lengthy and detailed section outlining the safety considerations:

https://www.anthropic.com/news/claude-fable-5-mythos-5#:~:te...

But none of which suggest that it is not useful for math or theoretical CS tasks. The biology classifier is so miscalibrated so as to render the model useless for biology; and yes, they hint at that on the label (but not the extent of it). However, there is no description or suggestion that it is so miscalibrated that it offers up refusals in completely innocuous theoretical tasks. If it is simply a state-of-the-art model for coding, and frontend design, so be it, but at least they should be honest about that.

It's not detailed, at all. It's all unnecessary verbiage and some meaningless graphs around "trust us, only we know what is safe". Meanwhile people run into these stupid "safeguards" on the most innocent queries. See e.g. this thread of discussion: https://news.ycombinator.com/item?id=48837404 Or indeed the very article these comments are under

Reply on news.ycombinator.com