[andy99]

#1 in a very close race is way less useful when you have to walk on eggshells to avoid triggering censorship (“safeguards”) that either refuse or knock it down to another model. I’ve almost completely stopped using Claude (except some legacy workflows) for this reason, reliability matters more than scoring 61 instead of 57. To me Claude is the most compromised and unreliable model (between the censorship and the id checking - which I have not experienced personally), it’s not worth whatever slight benchmaxxing they did for the latest release.

[afavour]

What are you asking that you’re so regularly running into censorship?

[areoform]

Things Fable's classifier has flagged, a non-exhaustive list,

    – "Does collagen supplementation empirically work?"
    - "Can you help me figure out how to calculate and generate Kaplan-Meier curve?"
    – "Why do rabbits reproduce so frequently?"
    — "Can you tell me how collagen peptides are absorbed by my digestive tract and the role they play? Can you teach me [edit: how] this works at the biomolecular level?"

[lwansbrough]

[loads up most intelligent AI ever created]

“Rabbit sex, how?”

[fallingbananna]

The question may sound ridiculous.

But isn't it more ridiculous that some company decided that the correct answer to such innocent and curious question is basically "That knowledge is too dangerous, you shouldn't ask that."?

[areoform]

I mean, yes. Why?

Why would nature encode such a ridiculously disproportionate / inefficient behavior when it leads to catastrophe so frequently?

I've tried to ask these machines dumber questions like, why castles? And... well I'm working on a few projects (mostly by hand) that they've helped with! :)

I like to ask dumb questions. It's fun. I encourage it.

[Alpha3031]

Lots of species are r-selected, I don't see why that would be considered inefficient. In fact I think there are probably more r-strategists than K-strategists.

[dleeftink]

Just as stating the wrong thing would be the quickest way to elicit a response in the past, so too can 'dumb' questions prime the context for more complex queries.

I am all for this strategy, and revisiting my list is equal parts fun and conducive to long-term recall.

[CamperBob2]

Answer: Because rabbits are tasty. If they didn't hit the ground hopping and bopping, the species would have died out long ago.

[kryogen1c]

Rabbits are a good input calorie to output meat ratio, and their excrement makes good cold compost. They breed and litter relatively easily. Theyre also easy to house.

[alightsoul]

Oh biology! It's dangerous!

[spicybright]

Even worse, it's offensive and kids could see it!!

[sigmoid10]

If it goes on like this, American AI will eventually be able to solve the Riemann hypothesis but deny the existence of nipples.

[mdp2021]

From the late Perscheid:

https://martin-perscheid.de/image/cartoon/3212.gif

("How do you reliably put an American out-of-combat.")

But the same vibe is felt outside the USA anyway (the uk came close to that attitude with declarations from starmer earlier this year).

[alain_gilbert]

The other day, I told claude that my physical wifi door unlock push buttons is a security risk because someone could run away with it and then unlock the door from outside whenever he wants. Then I told it that I want to introduce a concept of public/private key to uniquely identify my push buttons so that I can disable them individually using some crypto like ed25519...

Fable understood it as something along the lines of:

"introducing" "security risk" "using software" to "unlock door" YOU ARE FLAGGED

[JumpCrisscross]

> Fable understood it as

The dumbfuck bouncer Anthropic put in front of Fable decided this.

Fable is a PR model. It’s great. But if it were an employee, it would be the brilliant one who regularly shows up to work high. Not useless. But not reliable.

[spicybright]

Bet it has something to do with that new model being blocked by the US government. It was blocked for like a month but now that it's finally released they put the safe guards waay up in fear of that happening again.

[theplumber]

I bet it has something with Dario the drama queen begging the US gov to regulate them(I.e read ask them to put “safety guards” that they already had on hand)

[jpk]

> Fable is a PR model.

Yeah, Fable is Anthropic's Cybertruck.

[JumpCrisscross]

Not quite. Fable is a Model S. The problem is you have to buy a Cybertruck to get it.

[JumpCrisscross]

I wanted to explore some battery chemistry with Fable. It decided I was a terrorist, and then blew my session’s usage credits telling me to fuck off.

The current state of guardrails seems to be entirely about marketing to investors at the cost of customers. I’m switching to open models when my subscription expires. Almost everyone I know, including those with access to Mythos, plan the same at the earliest opportunity. (Or until one of the SOTA models leaks.)

[pmarreck]

What are you asking that you are NOT regularly running into censorship?

Pretty much everyone I know who uses Claude and works on anything with any level of detail has gotten false-positive flagged

I got flagged for coding in WebAssembly Text, for chrissakes LOL #haX0r

And honestly, Codex handles this better. It says "Things are going to go a little slower because we must perform additional checks on this. Is that OK?" and your only inconvenience is waiting a little longer.

Fable meanwhile just unceremoniously dumps you right into Opus without asking anything, it just tells you "you're in Opus now, sorryyyy!" Lame.

[gck1]

Reverse engineering. Codex sometimes displays an advisory prompt when classifier trips - "Wait longer while we evaluate this request further or use a dumber model". If you do nothing, it'll just take some time and almost always succeed.

It does require some brainwashing of the model to get it to the state where model itself agrees to do RE work though. But at least it's all predictable.

[simpsond]

I’ve had codex/sol block me due to safeguards tripping without attempting to do anything nefarious. It’s not entirely predicable.

[maCDzP]

I have had success with ”brainwashing” by starting out with bug bounties/CTF and then going from there.

[gck1]

That's brilliant, I should try that.

I usually just start by preloadig context with plausible legitimate use, have it work and obviously fail, and then ask to figure it out without ever mentioning any high risk words. Model offers to RE itself and classifiers are happy.

[msp26]

Asking fable to read it's own model card triggers this btw. Or asking if mitochondria is the powerhouse of the cell.

[skinfaxi]

Wait wtf. The mitochondria thing is true.

> Why this chat was flagged This model has safety measures that flag specific phrases. This can happen to safe, normal chats.

> Your message itself appears to be what’s triggering the safety check. Editing it and retrying may help.

[cge]

There’s confusion about the classifiers on Fable. They don’t ban chemistry and biology topics they flag as a potential risk, they ban anything related to chemistry or biology at all. This is intentional, and directly stated on the model card, but seems so absurd that there can be assumption it must be a misreading.

Being a researcher somewhat connected to chemistry and biology, Fable has been the most useless model I have ever tried. Essentially all work has instantly downgraded to Opus.

[stavros]

Anything biology-related does this. It even did it when I asked it how eye color works, or something about frogs.

[estearum]

Probably because the cost of blocking "is mitochondria the powerhouse of the cell" is nearly zero, while the cost of allowing "how do I synthesize the Spanish flu" is approximately infinite.

[areoform]

    >  while the cost of allowing "how do I synthesize the Spanish flu" is approximately infinite

I've heard this sentiment repeated elsewhere, but why? What makes you think that's the case?

Under this rationale, every serious HS textbook has "approximately infinite" risk. That's clearly not so. Why is this any special?

[actsasbuffoon]

The Bill Nye theme song is a threat to national security. That’s the timeline we’re living in now.

[Mistletoe]

Gemini knocks this out of the park, Gemini gang unite.

https://share.gemini.google/34vZzlnsmTaL

[mdgld]

I would love for Gemini to be competitive but even 3.6 flash doesn’t match sol, or opus 5, or k3

[Mistletoe]

It’s all relative, it’s competitive for me that just wants a free LLM that is like a turbocharged Wikipedia.

[wild_egg]

I'm doing a bunch of x86_64 assembly these days and Fable is simply not allowed to debug it. Hoping Opus 5 has a bit more freedom.

[Retr0id]

I haven't been using it for long, but so far the refusals seem about on par with how things were on Opus 4.8.

[d-m]

I took a photo of a rose bush and asked “what’s going on with this rose bush” which triggered a downgrade to Opus. It diagnosed it with rose rosette disease.

[actsasbuffoon]

I literally had Opus 5 flag a message because my hand was slightly too far to the side while typing. It apparently decided that a sentence that had some garbled words in it was a threat to national security.

[wewtyflakes]

I've hit it with intensely benign things; like asking it to make me a web-based client-side word game. I am guessing it saw the dictionary and pattern matched on various words, though ultimately it provided no explanation for why it triggered safeguards.

[weird-eye-issue]

Literally anything related to nutrition, athletic performance, etc especially if you ask it for research or sources

[AnotherGoodName]

Writing an implementation of a board game and one of the cards is called "microbes". Instantly knocked down to a lower tier model whenever it encounters that keyword because clearly bioweapons. Sigh.

[icedrift]

If you even broach language related to biology you’ll get rerouted. I was presenting data in a grid and referred to a grid cell, Fable saw the word “cell” and safeguards kicked in

[jefftk]

I thought we were talking about Opus 5, the model Fable now falls back to?

[eterm]

This thread is full of people talking confidently about their experience with a model released just hours before.

Either that or everyone is indeed talking across each other and talking about different things.

[bigbuppo]

I think the big take away is that Anthropic's products are hot garbage.

[rdtsc]

No op but my interactions with look like:

Me: "I got this crash in production, looks like a segfault, let's try to fix it. Here are some functions that might be responsible."

Fable: "No. This is cybersecurity, blah blah, I won't help you"

I forgot how I got it to fix the bug eventually. I think I convinced it that it wrote the code and made a mistake. But it was definitely a "Hmm, may be I should use another model" moment".

[actsasbuffoon]

I have way too many AI subscriptions. My favorite thing about Kimi K3 is that it just does what you tell it to do.

“Hey Kimi, penetration test my app,” doesn’t get me a refusal, a guardrail, or anything like that. It gets me a pen-test result.

[patcon]

Working on dimensionl reduction algorithms, I hit it all the time. I'm also trying to port related protocols from single-cell transcriptomics to collective intelligence systems (working with people x reaction matrices as analogous to single-cells cell x gene matrices.

Something between single-cell work and advanced nonlinear DR methods (perhaps used in alignment work?) it always flags me

[fluidcruft]

I haven't had a chance to try Opus 5 yet but Fable currently refuses to do anything in my field (radiology image analysis). It didn't used to be that way but that has been the reality the last two weeks or so. Fable has been useless they might as well drop it as far as I am concerned.

[mdgld]

Are you more on the medicine side or the ML side? I don’t see many other self-admitted medical people on HN.

[fluidcruft]

I'm more on the clinical physics side building tools for scanner/equipment QA and data handling/workflow automation/de-identification and anonymization but I also build random little tools to help optimize acquisition parameters.

[kami23]

I've noticed a few self identify and other random occupations, cool to see those fields checking out this tech at a deeper surface level.

I'm just a dev, but I appreciate the insights from other professionals.

[epistasis]

I use lots of biology in my day job.

Asking Fable 5 "Why did the chicken cross the road" results in switching back to Opus 4.8. I'm not joking, it really censors that, and I'm not alone in the result.

The memory aspect means that your prior work has a huge impact on what gets censored.

[smoe]

Not OP, but I got downgraded almost every time I had Fable implement something with security implications. Codex reviews it and identifies potential security issues, but Fable refuses to address them and downgrades instead.

[rzk]

I had a long session about SQL with Fable and at some point, it started to falsely trigger censorship for any message I write in that conversation, even for the simple string: "random message."

[Tostino]

Trying to have it do some rework on a patch to Postgres I'm working on, it just completely shuts down. The reported issues were with privileged escalation and I was instructing it on how to fix.

[arcanemachiner]

I was profiling a slow machine the other day, and triggered the safeguards.

I've been saying this a lot lately, but it doesn't bites you until it bites you.

The more you use the clanker as a general purpose fix-it tool (goodbye manual NeoVim configuration, you will not be missed!), the more you will find yourself bumping into these safeguards.

[theplumber]

Fable refuses to work on a login/signup system for example.

[OkWing99]

Ask anything related to practical applications for quantum-computing, or space etc. The stuff you can find on Wikipedia.

They were able to solve coding, but not what a real danger is.

[cute_boi]

Just ask math question and it will censor that. Even Misanthrophic employee confirmed that.

[__MatrixMan__]

I'm not who you're responding to, but I have a lot of questions about molecular mimicry: evolution pushes pathogens to be shaped like human cell surfaces because that way the immune system won't attack the pathogens (since, by doing so it would also attack the body). It's thought that many autoimmune disorders have an undiscovered pathogen as their cause, one whose mimicry caused such an attack. Discovery of these pathogens could be done computationally, I think. We can catch MHC binding event in process, find the bound protein, figure out which pathogens have genomes that code for proteins of similar shapes (epitopes), and we'd find--I hypothesize--a list of candidate pathogens for the cause of a delayed onset autoimmune disorder. Preventing these infections ahead of time would be a huge win against diseases like multiple sclerosis because without the initial exposure the immune system wouldn't have cloned so many of the cells that are attacking the host.

Claude was utterly useless in my attempts to write a paper about this. Wouldn't even help me search for sources. I guess you'd be asking the same questions if you wanted to develop a pathogen that could reliably evade the immune system.

[dylanowen]

I was trying to debug/fix a segfault in the JVM which kept getting flagged

[Levitz]

I routinely get into blocks when running medicine-related material through it.

[jbritton]

I was flagged for basically answering yes to what Claude suggested to do, which was test commands on a port for my code for tests we had been discussing. I really think it was flagged simply because the words test and port were in the prompt. Their filters are pathetically poor.

[thousand_nights]

i do homebrewing and asked it to compare some beer yeasts for me and hit the safeguards because... biology i guess lol

[idiotsecant]

The better question is how would you not? I got demoted to opus from fable for asking if a cancer vaccine I saw on YouTube based on frog bacteria was a real thing. I've gotten it for asking how encryption works. It's incredibly touchy.

[villish]

It's definitely not benchmaxxing from my experience with it. I have a test I use on all the models to create a game and Opus 5 feels like a generational leap compared to the rest. Benchmarks don't paint an accurate picture, you have to try them for yourself.

[chamomeal]

Even compared to fable?

[villish]

Yes. I've since watched a couple review videos on YouTube and all the game tests I've seen Opus 5 produce are incredible even compared to Fable.

[gck1]

Every time an online chatter (e.g. "limits are better", "model is better") makes me to reevaluate my principle of never paying Anthropic, I go to the model card, which strengthens my belief in the principle.

Why is Anthropic is so hell-bent on this auto/silent downgrade? Do they have a single user who prefers an auto-lobotomization instead of a refusal? Have they learned nothing from the backlash the first time?

[kccqzy]

Just go to /config. The very second configuration item is “Switch models when a message is flagged” and presumably you want to turn this off.

Oh but then you said you never pay Anthropic so you haven’t actually used Claude Code yet. Why would anyone listen to the opinion of a non-user?

[nananana9]

Not a great line of thought in general, sometimes the people who aren't doing the thing are the only ones worth listening to.

"You aren't repeatedly slamming your head against the wall. Why would anyone listen to the opinion of a non-wall-head-slammer about the merits of wall-head-slamming?"

[kccqzy]

I don’t really fully trust people’s opinions unless they have first-hand experience. So I would trust someone who has tried the thing and found it to be bad idea, much more than someone who hasn’t tried it and is merely repeating common tropes or talking points.

[gck1]

> so you haven’t actually used Claude Code yet.

Where do you think the principle came from? I've used claude code for a year, and stopped February this year.

[krzyk]

So when you turn that off will you get answer from Fable?

[markasoftware]

I don't believe they do silent downgrades right now, they're loud about it.

[buzzerbetrayed]

Yep. I cancelled my Claude Max subscription 2 weeks ago after feeling like Anthropic was doing everything it could to fuck with my day to day. Their lead would have to become significant for me to ever go back.

[joinjune]

I told Claude Opus 5.0 to use a global api key for a PFAAS to deploy some web applications in a test environment and import some data into them. It balked at using a global api key because the security issues surrounding the permissiveness run afoul of it's sensibilities.

I have done this task with Opus 4.5, Opus 4.6, Opus 4.7, Opus 4.8 and Fable, without issues.

I have done this task with Codex 5.4, Codex 5.5, and Sol 5.6 without issues.

Opus 5 is too cautious to be productive for me. It needs more tuning.

[NamlchakKhandro]

The utter meme-think direction this company takes with regards to sycophancy of its models is disgusting.

[mrloopex]

Maybe you just aren’t doing anything meaningful. Terrence Tao doesn’t whine about woke AI models.