Ask HN: Fable Thread (July 12th Edition)

2 points by andai ↗ HN
So, we just got an extra week of Fable.

https://news.ycombinator.com/item?id=48821102

Thought this would be a good chance to ask everyone how it's going, what the experience has been like so far. Tips and tricks, etc.

I've been using it for some major refactoring, but I'm running out of Fable usage so I've been using Opus for most of the work. I'm not noticing much difference there, so I'm probably not working at a scale where there is much difference.

Some people have mentioned that going back to Opus felt painful so I'm wondering what that's all about.

Anyway, yeah. Discuss :)

11 comments

[ 5.8 ms ] story [ 27.3 ms ] thread
Very expensive, not sure how it fits in with many companies seemingly trying to get employees using models at about Sonnet tier pricing. I certainly would never pay API rates for it, using ccusage I am seeing myself "use" $150-$400 worth of fable per day. (https://www.theinformation.com/articles/tesla-caps-employee-...)
That's funny. Sonnet is not great in my opinion. I mean, it often amazes me with its creativity, and I do prefer its style over most bigger models from other providers.

But it also constantly just does dumb things that make me slap my forehead. Opus is a lot better but the slap ratio has not reached 0 yet. Fable seems a bit better there, more testing needed.

But yeah, VC money ran out, now we wait for Moore's Law... :)

--

Re: Sonnet-ish-pricing. GLM-5.2 is cheaper than that, and appears to be "Opus-ish" in quality. I've been having a reasonably fine time with it. My experience is that it's "very solid for small and medium tasks", haven't tested it for anything bigger though.

I use GLM 5.2 through Opencode Go, but find it to be quite slow when you get to higher contexts (80k+) through their provider so I have not been able to test too much.
Do you have numbers for how much you were spending on Opus before with ccusage?

Fable should only be twice as expensive, but I think it does a lot more work by default.

Fable has seen an increase of at least 3x daily spend on my part, but it is also easier for me to reach my limit on my plan, so maybe I am just making more use of my limits?
For coding Opus 4.8 with ultracode is near perfect and doesn't grind away as many tokens. Fable is advertised as 2x the tokens but in my experience it is closer to 5x what I burn with Opus 4.8.
Do you mean in tokens or in $?
I only use Fable on things Opus 4.8 would struggle too much with, and as my harness improves that’s less and less. That or they dialed up the intelligence on Opus.