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

Fable 5 is Back

twitter.com

Post reply on HN
Print view View original

401–410 of 438 posts

Re: Fable 5 is Back

#401

Post by ngruhn »

nickalaso wrote: post #393

It is surprisingly half baked for something the company seems to be proudly charging my first born child and both of my kidneys for. Especially considering its all for the privilege of getting half way through a standard dev task before it just bricks out of nowhere on the 'safety' guardrails because of a keyword that often appears to be created by the model itself? I've been running Fable on a few different projects…

Imagine a nuclear power company being extremely cautious with safety and everyone online is like "make more power already you pussies!"

Re: Fable 5 is Back

#402

Post by hirvi74 »

mohamedkoubaa wrote: post #258
hirvi74 wrote: post #113

Earlier quoted context omitted.

What about quality? Being cheaper and faster, while great and all, is less valuable than quality to me.

You can always have opus review the result at the end

I've had bad results with this method. If I ask any model to review the same code ten times, then I will get ten different answer.

Re: Fable 5 is Back

#403

Post by benny_s »

I have the feeling it isn't as good as it was 3 weeks ago (not including the times you get downgraded). I mean it's still great, but in my memory it was better. Anyone else?

Re: Fable 5 is Back

#404

Post by lishuaiJing03 »

senordevnyc wrote: post #338
yokoprime wrote: post #169

i did use Fable for a brief moment the last time around, and apart from being extremely expensive, it wasn't any order of magnitude better than Opus or even GPT-5.5 for my workloads (development, prototyping, some api testing). I probably could manage indefinitely on Sonnet class models

Does it need to be an order of magnitude better? I run a piddly little one man SaaS company that’s doing about $30k in MRR, growing at about 10% per month. My AI coding costs are like $500 / month on average, but I’ll gladly spend 10x that to double my growth rate. I blew through about $400 in Fable usage in six hours before it got yanked, and it was money well spent. The alternative to that six hours with Fable was…

That is super cool. Checkout this repo which might give you super power to code quality and cut down 80% of token cost while keeping fable running longer jobs. https://github.com/syncable-dev/memtrace-public?tab=readme-o...

Re: Fable 5 is Back

#405

Post by dabbz »

janalsncm wrote: post #298
dabbz wrote: post #265

Earlier quoted context omitted.

I mean if you want to spend $200, and get a guaranteed amount of tokens in return you should be using the API. I agree there should be more transparency what 20x gets you that 5x doesn't. Though I also imagine it's a tough problem when you could be using Dispatch, Cowork, design, chat, code, etc. All of which use different contexts, models, and resources. I'd argue they actually need to either simplify their offering…

If products use different amounts of tokens, that’s fine. That’s fundamental to the products. But that’s the numerator, which they aren’t telling you. I’m also saying the denominator isn’t clear. One day it might be a million. Tomorrow 2 million. The next day 800k. Who knows.

I agree that would improve transparency but it'd also lock us and Anthropic into a situation where changing that would require new plans, prices, notifications, legal, etc. I think the fact that we don't see tokens shows just how subsidized the plan is. Which is mostly the point. They want us getting used to just using the product, not tracking tokens (for whatever behavior that builds later on).

Re: Fable 5 is Back

#406

Post by vonneumannstan »

signatoremo wrote: post #175
vonneumannstan wrote: post #119

Earlier quoted context omitted.

Its like saying Pinochet was one of the least murderous authoritarian dictators. The bar is low...

Where are Chinese companies on your scale? Mistral?

You can assume they're more or less co-opted by the CCCP so how much do you trust Xi? Mistral isn't even a real player.

Re: Fable 5 is Back

#407

Post by skarz »

ngruhn wrote: post #401
nickalaso wrote: post #393

It is surprisingly half baked for something the company seems to be proudly charging my first born child and both of my kidneys for. Especially considering its all for the privilege of getting half way through a standard dev task before it just bricks out of nowhere on the 'safety' guardrails because of a keyword that often appears to be created by the model itself? I've been running Fable on a few different projects…

Imagine a nuclear power company being extremely cautious with safety and everyone online is like "make more power already you pussies!"

Are we comparing nuclear energy to an LLM?

Re: Fable 5 is Back

#408

Post by Jweb_Guru »

Jweb_Guru wrote: post #100

Not super impressed, but I doubt my requests are getting routed to Opus -- it just doesn't seem to be as good at mathematics as it is at code (I found this to be the case last time it was released as well).

Yeah confirmed with more usage today. It seems ~ on par with (if not slightly worse than) 5.5 on math-oriented stuff.

Re: Fable 5 is Back

#409

Post by RichSchutt »

Fable 5 is functionally useless not just a regression of the original Fable. totally useless not to mention when it flags your code you may have noticed in the original release the models internal reasoning was not viewable it is intros release and mines. internal thought process said I am Claude Sonnet 3.5 when I asked it what model it was while it answered I am Fable % in the chat window. And to be fair it was about as useful as sonnet 3.5

Re: Fable 5 is Back

#410

Post by nar001 »

ngruhn wrote: post #401
nickalaso wrote: post #393

It is surprisingly half baked for something the company seems to be proudly charging my first born child and both of my kidneys for. Especially considering its all for the privilege of getting half way through a standard dev task before it just bricks out of nowhere on the 'safety' guardrails because of a keyword that often appears to be created by the model itself? I've been running Fable on a few different projects…

Imagine a nuclear power company being extremely cautious with safety and everyone online is like "make more power already you pussies!"

Sorry this is a very bad analogy, nuclear power isn't the same as a LLM, and definitely not as dangerous either. This is ridiculous.
Post reply on HN