[zzleeper]

I tested Fable through Cursor; asked for ideas on how to make a data website I have less "Claude-like" (IYKYK what are the usual tells), and it spun out the most useless, Claude-like CSS styling ever, wasting $40 in 10 minutes.

The website was created through Opus, so you could also say the results were worse than Opus. (This is just to say that I had the same experience using the US models, so perhaps those Asian models are Mythos-like lol)

[cheema33]

> I tested Fable through Cursor;

I tested Fable for a whole day. And my experience was quite the opposite. I was blown away. Admittedly, I did not try it through a middleman like Cursor. I used Claude Code CLI.

[josephg]

Me too. It’s output was fabulous. And it acted like a senior engineer - actually coding up hypotheses, testing them, finding problems and presenting good, usable recommendations backed by solid evidence and wisdom. It can probably do most of my job, which gave me a bit of an existential crisis.

I’ve paused my Claude subscription until they bring it back. Opus makes mistakes constantly, on every level of abstraction. Every time I look closely at its work I find problems.

[zeristor]

Opus 4.8 works like that for me. I have it writing ADRs, then my main architect worker challenging it.

[gwerbin]

Even Sonnet does that if you gently prompt it to.

[solenoid0937]

I also felt that Fable was mindblowing.

[nonethewiser]

If you actually give it an example of the style it can copy it well. even just screenshots of other websites or UIs. It just sucks at producing it itself.

[addandsubtract]

Why would the model know what "Claude-like" is?

[valleyer]

Well, in part because the phenomenon has been discussed on Web forums that (a) have at this point made their way back into training data and (b) are accessible in Web searches that the model can invoke. And in part because the model can "know" what its initial instinct is and "decide" to go against it.

[jazzyjackson]

Still it’s like asking an image generator to produce an image without an elephant. Just tell it what you want.

[ninjalanternshk]

It’s like saying “make this bad animal drawing look better, and like someone else made it” without telling them what animal was supposed to be.

[ninjalanternshk]

Yeah this is about the worst way you could imagine to evaluate an AI model.

If you’d given it a real task you’d have been impressed.

I was floored by the day I spent with Fable. Got weeks of work done.

[valleyer]

Oh, I was also quite happy with Fable. I was just answering the question asked.

[cevn]

Same. It was one shotting unbelievably well compared to 4.8.

[jaapz]

And 4.8 on xhigh was/is already pretty impressive