Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The classifiers Anthropic puts in front of Fable are too zealous

combine-lab.github.io

Post reply on HN
Print view View original

181–190 of 203 posts

Re: The classifiers Anthropic puts in front of Fable are too zealous

#181

Post by SwellJoe »

christophilus wrote: post #179
SwellJoe wrote: post #141

I've found in my current work on a security auditing harness and benchmarks, both Fable and Opus are useless. I recently switched to using GPT for Nelson and the security benchmarks I've been doing because Opus started refusing to do the work. I guess I probably could also use GLM or DeepSeek or MiMo, and I'll probably do some experiments to see the shape of all of their guardrails in this area soon, now that I see i…

This underscores a huge risk of broad agentic adoption in an enterprise. Your engineers atrophy and if the agent provider decides to squeeze you, you’re SOL.

Yeah, I guess I could also write the code myself, if all the models refuse. But, it seems worrying to have a handful of the largest corporations and a few governments having access to the best models while the rest of us are using hobbled ones.

So far, we're not in that boat. I've had two models refuse to participate, but most just do what they're told.

Re: The classifiers Anthropic puts in front of Fable are too zealous

#182

Post by meowface »

nolok wrote: post #109
meowface wrote: post #21

To summarize: the classifiers Anthropic puts in front of Fable are way, way too zealous and have way too many false positives. From my experience, the model itself is very useful when it isn't refusing any of your prompts.

It is, but it's also using tokens at absurd rate, I asked it to review the planned architecture for a medium scale project and it used my 5 hours limit on one prompt just zaaaaap, not even the fable limit straight up the full 5 hour session no more Claude for the afternoon thank you for paying you Max x20 sub. Hell it didn't even bother to finish produce anything worthwhile. And just to be clear, plan was already don…

Oh yeah, I've noticed the same, for sure. But that's basically what I was expecting. The best model is not necessarily always going to be the most cost-effective/sensible model for a particular use case.

Fable-class models will probably be cheaper for Anthropic to serve within the year, though. And rumors are GPT-6 is of similar size and intelligence to Fable and may come out within the next few months. OpenAI models tend to give you more bang for your buck, probably in part due to OpenAI being able to throw more capital and compute around on top of being particularly willing to loss-lead to stay competitive with Anthropic.

Re: The classifiers Anthropic puts in front of Fable are too zealous

#183

Post by gpm »

slowin wrote: post #104
gpm wrote: post #71

Earlier quoted context omitted.

Cost, the politics of the people involved, and that there would be no real need for secrecy around it (but lots of need for marketing) so we'd probably know about it. It frankly doesn't seem like it would be that useful either... the US knows how to build weapons of mass destruction.

I have to disagree. For the sake of argument say Elon Musk had his own personal, uncensored SOTA model. He has the cash and politics to make that a realistic goal. Would people want him to have that? Not really, hence secrecy as well.

Oh I really did mean "anthropic" and "fable class" in that paragraph. Different people in Anthropic's position would do things differently. But they're them and I think there's pretty good reason to think they really are the only ones with a model of that class so far.

Re: The classifiers Anthropic puts in front of Fable are too zealous

#184

Post by smcleod »

thierrydamiba wrote: post #86
smcleod wrote: post #81

Earlier quoted context omitted.

I've been working with it heavily since its first release. I use it for software architects, complex debugging and some development and I have not had it refuse or downgrade even once.

Have they ever talked about what goes into the classifier? I wonder how much your past chats impact it. For example if it knows you do X at Y company is it more or less strict?

Yes their docs cover how to properly prompt it to ensure you don't get hit by the classifier, you can distil those down to a skill to help build prompts for the more challenging situations, e.g. https://github.com/sammcj/agentic-coding/blob/main/Skills/pr...

Re: The classifiers Anthropic puts in front of Fable are too zealous

#185

Post by smcleod »

robot_jesus wrote: post #87
smcleod wrote: post #81

Earlier quoted context omitted.

I've been working with it heavily since its first release. I use it for software architects, complex debugging and some development and I have not had it refuse or downgrade even once.

Same. I really am curious if either 1) I am using it in genuinely different ways or 2) these people are being willfully disingenuous.

I suspect there's some cargo culting, and some folks that are generally more likely to table flip than understand things that challenge their workflow.

Re: The classifiers Anthropic puts in front of Fable are too zealous

#186

Post by jsw97 »

vient wrote: post #134
jsw97 wrote: post #128

I am wondering about the author's allegation that there is a user filter, not just a prompt filter. Of course it could also be the case that it is just a prompt filter, but Fable sees memories from the authors' prior sessions that cause a rejection. I wonder if the author could control for this is in some way, if Claude lets you run isolated session without memory access.

Author mentions trying incognito mode without success. I also tried their strictly mathematical problem description and got filtered 5/5 times.

You're right, I missed that. That really is troubling.

Re: The classifiers Anthropic puts in front of Fable are too zealous

#187

Post by nojs »

nomel wrote: post #138
azalemeth wrote: post #117

I'm a medical physicist. I literally haven't been able to get Fable to answer a question I have written -- all of my work is verboten. I have however asked Claude Code (opus 4.8) to ultracode "a Fable oracle that in a digraphed, clean content, isolated environment with a minimally scoped working codebase. Ask the model at the start and the end to report exactly what its version string is. If it is not claude-fable-5,…

My theory is that they included/didn't align-away extra biology/chemistry in the training in preparation to offer an unrestricted/less restricted model to pharmaceutical companies/trusted partners. This would necessarily require a filter between the, now more "dangerous", model. I always assumed this would be the eventual way to manage high intelligent/"dangerous" models, since all evidence shows that alignment makes…

> people said this would be too expensive

I imagine this is why the filter is so bad. Doing it with an intelligent model that better understands intent would be too expensive, currently.

Re: The classifiers Anthropic puts in front of Fable are too zealous

#189

Post by ares623 »

fragmede wrote: post #175
ares623 wrote: post #148

Earlier quoted context omitted.

How do you know? Is it really that obvious of a tell between Opus and Fable? My understanding is that they silently downgrade you.

No, there's a banner that says you've been downgraded.

Very considerate. But also, can we trust them that they're not downgrading without saying anything? The incentives are there, to bill at Mythos prices for Opus costs.

Re: The classifiers Anthropic puts in front of Fable are too zealous

#190

Post by bconsta »

mrandish wrote: post #162
vardalab wrote: post #18

Fable was refusing to patch vllm for me when trying to get mtp to work on r9700 gpus. Kept on bumping down to opus. Tried to really sanitize my prompts and everything but it seemed intrinsically prohibited from doing this sort of work. I guess it’s useful for making inane one shot games and websites, lol.

> Tried to really sanitize my prompts And in doing so, you probably got your account and prompt flagged for 'attempted jailbreaking' (apparently, such scores are remembered for up to 7 years).

Kind of ironic considering Anthropic hasn't even been around for 7 years.
Post reply on HN