Fable and the end of the free lunch • Hacker News Board

Re: Fable and the end of the free lunch

#21

Post by unshavedyak » Sun, Aug 23, 2026, 8:31 PM UTC

tonyarkles wrote: post #13

enraged_camel wrote: post #5

>> GLM 5.2 is worth focusing on. It came out the same week as Fable and is roughly 1/9th the cost (and ~1/5th the cost of Opus 5). Is GLM 1/9th the quality of Fable? Perhaps, for certain classes of tasks. But for most rote coding it’s more than sufficient. Especially when provided with great context. I frequently chat with Fable to interrogate and shape a design, before handing off a brief to GLM. People say stuff li…

Something I’ve found comparing between Fable and Opus is that Fable has impressively good analysis skills, but both of them seem to go way way overboard with “present state” comments “# We’re making this change here because of this issue blah blah, here’s what you need to know about np.percentile, blah blah” that I end up significantly pruning before making a PR. I let it do the same style verbose commit messages (be…

Those "present state" comments are the bane of my existence. It was present in 4.7/etc but i put in a ton of guards against that into my global memory and it worked quite well. Fable and Opus 5 regressed badly in this space though and i can't keep it from making those types of comments again.

Really frustrating.

Re: Fable and the end of the free lunch

#22

Post by tyre » Sun, Aug 23, 2026, 8:33 PM UTC

Jare wrote: post #19

enraged_camel wrote: post #5

>> GLM 5.2 is worth focusing on. It came out the same week as Fable and is roughly 1/9th the cost (and ~1/5th the cost of Opus 5). Is GLM 1/9th the quality of Fable? Perhaps, for certain classes of tasks. But for most rote coding it’s more than sufficient. Especially when provided with great context. I frequently chat with Fable to interrogate and shape a design, before handing off a brief to GLM. People say stuff li…

> my theory (which I unfortunately do not have the money to test and prove) is that a codebase designed and implemented by Fable would be substantially better than one that is designed by Fable and implemented by [others] I don't have proof, only my anecdotal experience: I leave plenty of Fable usage on the table because I do not think its implementations of code have been better to Opus 4.8, not even close. It overe…

As a counterpoint (data point of one code base), I had Fable lead development of a complex system recently (an end-to-end insurance claims billing system) as a test project. It blew me away. Opus could not have done the same, given the feedback Fable had to give when Opus would implement individual features.

Granted, I laid out a document with coding practices, architecture, and technical design recommendations to steer it towards good engineering. And it's a domain I know super well, so I could give very nuanced feedback on trade-offs + architecture. If it had been left to its own devices, maybe it would have over-engineered the h*ck out of it.

But the code it produced—and the implementations it guided Opus towards—were excellent.

Re: Fable and the end of the free lunch

#23

Post by dgellow » Sun, Aug 23, 2026, 8:34 PM UTC

hypfer wrote: post #18

simonw wrote: post #17

Earlier quoted context omitted.

5.3 isn't available as open weights yet, and only became available via API three days ago. Prior to that the only way to access it was via a Z.ai subscription.

[flagged]

FWIW you’re not looking good in this engagement, feels very childish, looking for a gotcha that doesn’t mean much

Re: Fable and the end of the free lunch

#24

Post by bellowsgulch » Sun, Aug 23, 2026, 8:34 PM UTC

farlight wrote: post #15

bellowsgulch wrote: post #6

Are people still using deepseek-v4-flash everywhere? I found after the price increases, mimo-v2.5 seems far more attractive.

It's been cheap again on openrouter for the past few days. No idea how long it will last, but I've been using it from Baidu over the weekend, and it was about half the cost of the old DS prices, before the increase. Looks like people are figuring out how to offer it for peanuts.

Awesome. Thanks for the heads up.

Re: Fable and the end of the free lunch

#25

Post by dude250711 » Sun, Aug 23, 2026, 8:35 PM UTC

moltar wrote: post #10

I just use Fable for reviews of specs and code then hand off to Opus to work on. Works well.

Does it not silently degrade to Opus if it does not like some word?

Re: Fable and the end of the free lunch

#26

Post by hypfer » Sun, Aug 23, 2026, 8:36 PM UTC

dgellow wrote: post #23

hypfer wrote: post #18

Earlier quoted context omitted.

[flagged]

FWIW you’re not looking good in this engagement, feels very childish, looking for a gotcha that doesn’t mean much

I think that depends on the audience. Thank you for caring though :)

Re: Fable and the end of the free lunch

#27

Post by dgellow » Sun, Aug 23, 2026, 8:37 PM UTC

mholm wrote: post #3

As models train up the intelligence ladder, many common tasks will hit fully diminished returns, and instead it'll just get progressively cheaper to do that task. But the tasks that AI is capable of doing are also expanding. I'm not sure 'Some tasks don't require the peak of the frontier' is worth worrying about, from an AI finance perspective.

It’s worth considering for companies paying API prices, and not relying on a subscription quota

Re: Fable and the end of the free lunch

#28

Post by blfr » Sun, Aug 23, 2026, 8:38 PM UTC

What are all these rote coding tasks people do that they can farm it out to lesser models?

Re: Fable and the end of the free lunch

#29

Post by a2ff6eeb0 » Sun, Aug 23, 2026, 8:40 PM UTC

mholm wrote: post #3

As models train up the intelligence ladder, many common tasks will hit fully diminished returns, and instead it'll just get progressively cheaper to do that task. But the tasks that AI is capable of doing are also expanding. I'm not sure 'Some tasks don't require the peak of the frontier' is worth worrying about, from an AI finance perspective.

Exactly; so far, we've only replaced the need to design algorithms and hand-write code; what if we apply the same effort towards the skill needed for system architecture, project management, and the rest of the SDLC? Or even outside of software!

Right now, it feels like all of that is today where coding was a year or two ago, and we're on the cusp of some massive improvements outside of coding. It'll be interesting to see what these companies decide to automate next.

Re: Fable and the end of the free lunch

#30

Post by jml78 » Sun, Aug 23, 2026, 8:41 PM UTC

tyre wrote: post #16

mholm wrote: post #3

As models train up the intelligence ladder, many common tasks will hit fully diminished returns, and instead it'll just get progressively cheaper to do that task. But the tasks that AI is capable of doing are also expanding. I'm not sure 'Some tasks don't require the peak of the frontier' is worth worrying about, from an AI finance perspective.

Yes. I use Opus for tasks that Sonnet could probably handle, but I'm not hitting my quota. Whatever minor incremental gain is "worth it", since marginal cost is zero. Even now, I use Fable as the planner and coordinator, with it farming out to agents. I don't hit my Fable limits either. Which means I could accomplish more, but these are side projects so I don't need 30x productivity. Still, claude is constantly churn…

I operate mostly in the devops arena. Lots of things opus is fine for. But there is just things where I can hand hold Opus through changes, or I can ask Fable to do it and it gets it right on the first try. People will say let fable plan and validate with opus doing the work. I found that burns fable tokens even faster because opus makes so many mistakes, fable has to review things 4-5 times before opus gets it right. A single fable implementation at medium or low effort would have one shot it.