Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- “ Claude Fable 5.1's writing is generally a step up from earlier Claude models, with fewer stock phrases and less unexplained jargon. In some cases, though, its prose is denser than Claude Fable 5's: sentences run longer and there are fewer paragraph breaks.”
I cancelled my pro max Claude subscription last week; codex is much more succinct. I am curious if this is getting better.
I don’t think Anthropic realizes that humans have a token limit too and it can be exhausting to read Claude’s output. Prose density is not the same thing as succinctness.
by tarr11 - Just the other way I was thinking that if I asked "What does Lamborghini do?" the only correct way to answer is a single sentence "Which Lamborghini are you referring to?".
But LLMs will fail at this question: they will tell you about Lamborghini's latest car and mix some history in it. Just try.
Which is the wrong answer anyway, because there's at least two major companies called Lamborghini, one making cars, one making agricultural equipment and at least one famous person (Elettra) with that family name.
This very simple test/question makes me realize how much do I hate LLMs in a sense: while I agree that the answer it gives is the most plausible for 90% of the users, it's ultimately both wrong and long. And that 90% compounds.
But there's no "correct" answer in my eyes than "who are you referring to?". Possibly without listing all the possible Lamborghinis.
by epolanski - I switched to using Codex for the last two weeks, and while the prose has been better, there have been a lot more technical oversights. I'm now having fable review codex commits and it finds deep issues. I'v also done the reverse where opus/fable do the work and then I have codex revise all of the prose prior to reading anything myself. This has also been effective; I'm not sure which is the better approach.by gwking
- Amen. I would trade some stupidity (say ten points on any benchmark) in exchange for a version of Opus or a similar model that actually gave me direct, concise answers.by hungryhobbit
- > Prose density is not the same thing as succinctness
Can't agree with you more. I review 2-3 PRs a day from my team of eight data engineers. Most of my team members use Claude to write SQL, dbt and Python code. Some of them use Claude a lot, some less so. I can easily tell when I review the code that is mostly Claude generated vs. the one that is not. In dbt models where we have a lot of biz logic in intermediate layers, that's where I really have a difficult time following Claude-generated comments. So much jargon copied over from other adjacent dbt models (yet inconsistently), and the prose is super choppy (for the lack of better word).
After reading a looooong sentence/comment line, I still can't figure out what it really means. Had to always re-read the line 2-3 times (sometimes, more) to sort of understand. Reading code, however, is so much easier and usually, I just skip to reading the code and then come back to the comments. :D
- I've developed a habit of adding into my prompts "please keep your response concise and succinct" or "I'm trying to cram, please only provide the minimum level of technical detail necessary to understand this topic"
I find it helps immensely but it'd be nice if I didn't have to do that.
by precision1k - "Humans have a token limit too" - that's so good and it explains so much of the fatigue that myself and colleagues/peers have about Claude in particular.by andreidbr
- I just can't stand how often Claude says something like "And the honest part? It's..."
Like, were the other parts not honest? I don't understand how Anthropic let it get like this, it's been such a clear regression
by peab - One thing I've noticed and HATE, is that when you increase thinking-effort, that seemingly increases response-length. Meaning that X.High is longer than High, which is longer than Medium, etc.
Which is kind of the inverse of how people work; a really smart person can condense difficult ideas into simple[r] terms. Whereas people who struggle speak a lot but say very little.
High/X.High do seem to deliver better quality results, but it sometimes feels like needle-in-haystack extracting that from the word vomit.
by Someone1234 - "Price. Fable 5.1 will cost an estimated 25% less than Fable 5 for typical workloads, wherever usage is billed by token. This is because we’re reducing our pricing on cache reads (where the model reads inputs that have already been processed and stored). For highly agentic work, the savings will often be much larger—up to approximately 45%."
Glad to see this!
by pookieinc - I hope that this also applies to the Subscription usage. As that can then stretch out Fable usage by a lot more.by benjiro29
- And then you see this:by scrollop
- The big issue they face right now is that vastly cheaper open models are proving capable for more and more uses at cents on the dollar.
This is the right direction, but they aren't going to get there fast enough.
They will list, investors who don't know anything about tech will buy, the world will realise that China just put out a model that is good enough at a fraction of the price, they will crater.
by ActionHank - This is just cache reads. In real usage it costs 15% more than Fable 5 -- all for marginal gains.by george_max
- To be honest, these frontier model releases have become boring for me. Opus 4.8 was already good enough for most of my use cases. I don't have any projects right now that I would use Fable for instead of Opus. So when I see announcements like this I just think "that's cool I guess" and then go back to using weaker/cheaper models.
What's far more exciting right now is models like DeepSeek V4 Flash and GLM 5.3 Flash. They have achieved good-enough-intelligence at extremely low prices and fast speeds. I don't have a use for Fable-level intelligence, but I do have uses for Opus-4.8-level intelligence that I can use as much as I want without worrying about the bill.
by EliasWatson - fable and friends are useful for long-term agentic stuff like orchestrating glm-5.3 flash implementers and verifying themby aschobel
- if you use these things to generate design docs / text, it should be good news if it is actually better at prose as advertised. Some people like sol for prose better the anthropic models.by harshaw
- Try to solve more ambitious problems.
Something we don't actually know how to solve.
by fooker - I have a project that could use Fable, that fails horribly on Opus, Sol, Grok, Gemini and GLM etc, but I just can't afford to use it on something so frivolous. (Assuming Fable could complete it)by qingcharles
- Not to mention you can actually see the tokens you pay for, and you can finetune it or change its system prompt.
I think compute providers are the big business. Run any model you like, adjust the weights however you like, adjust the prompts and behavior however you like, but we'll provide all of the hardware infrastructure for you at a renting fee.
by nullbio - I agree that intelligence at cost is exciting right now, especially if you view AI as a tool. The clock is ticking on subsidized tokens and cheap or free local inference will be the future. I think people want AI to be an oracle for prediction and discovery, which is where the sota models come in. But each release seems more iterative and underwhelming than the last. When the latest models regularly reveal unexpected insights, like how to get my execs to stop demanding hand-wavey 10x productivity gains, somebody let me know.by disfictional
- GLM 5.3 Flash has been a relevation for me. It's practically impossible to spend more than $5-$10 per day if you're only working on a single project -- but $10 is a full-day of continuous churn. First I was super sceptical about it, and always used Fable to instruct it, but now I realised that even with complex coding, it's reasonably good.by sz4kerto
- The human brain is fascinating Three years ago The idea of having A robot writing production level code in 10 minutes that would have needed a team of 5 people and 2 months. Was pure Scifi
Now it's boring , not good enough
Wow there should be a term of that .
by kbrannigan - "Distillation is a safety risk, since the distilled capabilities can subsequently be released without adequate safeguards."
Can't believe they haven't at least figured out better messaging. If we take them at their word, it's hard not to read it as a messiah complex, that they think they're the only ones capable or worthy of making these decisions. I don't believe them, but I wouldn't be surprised if the articulated reason is a version of "distillation is a safety risk because we might lose the race".
Plus, completely deaf to the recent OpenAI-HF hack incident. Recall, defenders were categorically unable to use western frontier models in their response.
I was originally going to complain about the chem and bio guards still being too onerous, but I'll admit the projects Fable 5 categorically refused to work on are now usable, at least not rejecting on first prompt because the word "virology" was in a git commit (absolutely serious, in one repo it triggered on literally any prompt, eventually traced to the system prompt loading git commit history). Still, them trying to get into the biomed business while walling off the capabilities to the public reeks. Why sell the segments that are actually valuable if you can capture the value yourself!
by rcr-anti - It definitely leaves a bad taste because it is completely transparent their concern is not security here and that means they are lying / misrepresenting this to our faces - which then raises the question of whether you can trust them on other things.
Would you let someone who lies to your face write code for your sensitive internal business systems?
by zmmmmm - > Can't believe they haven't at least figured out better messaging. If we take them at their word, it's hard not to read it as a messiah complex, that they think they're the only ones capable or worthy of making these decisions.
Can't say I had such troubles actually, no. Their position can be extended to any and every model provider just fine, it does not single them out specifically.
Surely there's a less hyperbolic and ad hominem-y way to take issue with this? I don't think following up a critique about ineffective messaging with one centered around a demagogue reach is particularly compelling at least.
Their argument is that the model provider owns the safety story, and that as such, they consider the extraction of capabilities (which washes the guardrails) as a failure on their side. If this makes you think of personality traits, I'm not sure you're engaging with their position earnestly. It most certainly doesn't leave me any more equipped to disagree with them either.
If you instead highlighted how awfully convenient it is, however...
by perching_aix - > For example, in testing by the investment firm Millennium, Fable 5.1 found the cause of a rare crash on their internal systems that none of their engineers (or any other model) had been able to explain after several years of trying.
Say what you will about LLM-generated code, but stories like this give me hope that software will never be as buggy as it once was.
by jumploops - You have a serious engineering problem if you're not able to find the source of a crash after years.by Thaxll
- I sometimes have that feeling too, then ask another LLM to do a code and vulnerability review and OMG: rookie mistakes, over complications and security gaps even a 1st year student would not make regularly.
So.. one more year of untreated bipolar AI psychosis I guess..
by PedroBatista - > Say what you will about LLM-generated code, but stories like this give me hope that software will never be as buggy as it once was.
Stories like these is what I now call 'Marketing slop'