I’m in the same boat. Though I will occasionally use Fable to review things to see if it can pick up anything but I’ve honestly not found it to be any more effective than Opus.

I’ve found that Fable is good when the model intuition really matters. For instance, picking model architecture in a machine learning problem. Opus will grind the implementation just fine, but having intuition for picking a good research direction is better with fable

I only use Fable 5.1 when I'm able to start on a larger feature within my work's codebase. Most tasks can be done by Sonnet 5.5 or Opus 5.5 so I don't fret, especially if I understand the technical aspect of what's being done, e.g. user's dashboard gets a new button to do X thing, error happened b/c we didn't catch it the first time around.

For Fable, I really like to think of it as the heavyweight reviewer whenever I'm about to start so I save myself some security and/or glaring technical issue.

LoC doesn't tell full story.

It could be flat web app with frontend -> api -> db later, or some very complicated system with many components and edge cases. Imo, in second case, Opus still have lots of struggle to understand system as a whole.

I have a rocket trajectory optimizer that creates a large-ish (~1000 variables x ~1000 constraints) NLP and feeds it to an SQP solver inside this codebase. Not just a REST API over a database.

I guess I do have an outstanding hard problem where the SQP solver crawls across a flat-landscape. Opus 5.5 correctly tells me that is the problem, but isn't very useful in solving the problem (it has helped a bit with solver tuning, but it doesn't really know how to fix it). I have a hundred other bugs and refactoring I can do with Opus 5.5, though, where it happily chews through pretty complicated tasks for me with reasonably light hand-holding. Maybe this Saturday I take whatever credits I have left for the week and throw Fable at it and watch them evaporate.

Another dimension is:

It looks like you are working on some experimental system which is not critical atm, so you can mess around, create/fix bug, build prototypes and check them, do research of approaches, etc.

Now, imagine you have similarly complex system, but every second of downtime or bug produces lots of damage. In this case, you can't afford low intelligence vibe coding.

The fact that you deal with hundred of bugs, means that your Op5.5 won't work for second case.

I am in the exact same boat as you. Opus 5.5 on High solves all engineering problems i encounter in my SWE job. If it doesnt do well, its nearly always requirements engineering: I did forget to specify something or there was a misunderstanding. Or taste approach wrt to architectures chosen. None of these are really different if I use a stronger model.

I am also happy with this current state, as I believe it will at some point allow me to transition to open models once they reach the level of opus 5.5. high. But its probably futile to try predict the future in these times.

> None of these are really different if I use a stronger model.

That's true till it isn't, though. It's why it's always worth trying stronger models when they come out.

Sure but they’re the harder problems.

Eg. https://tfmbot.com is an implementation of a popular board game. Opus and even sonnet handle that part. Each week i spend my remaining credits on fable to think how to improve the ai opponents. It plays at a very high level (can get into the top 100 on BGA if i let it). Opus alone couldn’t get it to the level it’s reached.

If you understand your problem well and know 80-90% what you want it to look like (or it just isn't very hard), it's just more cost effective to use a smaller model. Even Opus is overkill for a lot of the work I do. Most code I produce is from Luna Max implementing against fairly prescriptive plans made by bigger models.

Yeah, I just threw it into a refactoring problem, and it started to produce a mess because of a bad API I decision I made 5 years ago (when I had no idea what I was writing). So stopped it, went back a step, fixed that very old piece of tech debt, then asked for the refactoring again and got exactly what I wanted.

Yeah its not for writing your average software. In fact its actually inferior to Opus generally for that generally.

It is for hard problems. Mathematics, Physics, complex software architectures and designs like large scale distributed systems. Things that you've been trying to do for 10 years and fail at every single day, and keep waiting for a smarter model to come along to see if it can solve the problem. That is what Fable (and Gemini Argon/Carbon) are for.

Don't use them to make a web page or a rest API. That is a waste of money and time.

I'm cleaning up old, unintuitive code that is badly architected all day long. The previous developers used stupid patterns and bad naming schemes and created tons of unnecessary complexity. Everything is so interconnected that it’s like defusing a bomb when trying to refactor... Yeah, I feel I’m nowhere near where I would want to be in terms of capabilities, even with Opus 5.5.

But the improvements in how well the model does the work are noticeably better with every good model release. As of now, orchestration of agent pipelines is ALMOST so good that I can point it at a problem, and it will solve it safely and reliably without making a mess. But it requires an agent pipeline with context gathering, refactoring, attack sessions, a sprinkle of Sol 6.1 for bug hunting, and Sol 6.0 for Daybrak security audits, and a final de-bloat/clean up pass. I’m feeling that we’re getting close to doing a lot of the work fully agentically. But I can absolutely "feel" that we are not there yet when it comes to the intelligence I need. I need moar!

On my 100 person engineering team's monorepo, every model is better at better at detecting subtle bugs as it works -- reliability goes up and thus I'm further moving faster. (Most of my work is brownfield style refactoring).

As said in other comments, when dealing with a not perfect codebase, a smarter model can be really helpful. A smarter model is also better at understanding intentions in the prompts. Some of my tasks require a big detailed prompt but finding the assumptions is really demanding (for me), so a smarter model helps.