Comment by p1necone
4 hours ago
I have a pretty large, complex project I've been building with heavy AI use (new language + compiler). I was following a 'strong model as orchestrator launching cheap models as implementers' pattern, but I recently trialled just using Deepseek-V4.1-Flash as the model for both layers because of the cost savings (with mimo v2.6 flash on code review agents for some decorrelation).
I was previously using GLM-5.3 as the orchestrator, after switching to DS anecdotally there was an unnacceptable quality loss, mostly around not taking all the relevant context into account when making decisions, pulling new design out of thin air without discussion too often, and being way too wordy and rambly in documentation despite prompting to avoid it. There's a lot of docs, rulings, core concepts, design philosophy to uphold and DS was just not cutting it.
However, it's perfectly capable of being the sole agent for all of my well specced implementation tasks. I've gone back to GLM as the orchestrator.
On the Claude side of things I was previously following "strong model directs weak" with Fable directing Opus/Sonnet (its choice per-task). Since Opus 5.5 came out I've just been having Opus direct Opus.
The sub-agent separation is still valuable to keep context clean for the orchestrator, but I just have no reason to use Sonnet as the grunt-work implementer because I'm finding it hard to run out of tokens with Opus 5.5 on a $200 subscription plan. It's really really good at subjective quality of work per token used.
I would probably go that route if I could use other harnesses with claude models, but I don't want to be locked in to claude code, and their API pricing (which you need to use it with other harnesses) is so much higher than subscription.
plenty of harnesses use the claude subscription
My work pays for Claude and cursor.
I have actually just dropped to using sonnet for everything, sure it does need some directing but I have yet to see a need to jump to opus.
To me it feels like sonnet/terra and composer 2.5 and grok 4.7 are actually good enough for most tasks and these companies are pushing the high models simply to make money.
If you're not using the Superpowers set of skills, give it a shot. It's been working really well for me on a variety of tasks.
Can't wait to just use the hand made Jai and laugh at everything else built with AI :)
You can just use plenty of good handmade languages now, I'm not claiming mine will ever be good or useful to anyone other than myself. I'm using AI so heavily on my project because I want to explore the PL design space without spending years on implementation for things I'll probably want to throw away and rewrite a different way once I actually play around with them properly. And because I lack the motivation to persist through the sheer volume of grunt work that language implementation needs to get to the juicy interesting parts.