I have a stage-gated workflow that prioritizes “premium” token efficiency (Fable.) and getting the most out of my subscription services. (Which boils down to Fable running carefully prompted deepseek-flash agent teams that defer back to the managing agent for any design decisions in most work.) As part of that workflow the manager uses cheap reconnaissance agents to burn their tokens in order to build relevant repo context, instead of the managing model’s. I’ve been doing this since they released Opus and it occurred to me that most of my pre-implementation phase token use was going right into the garbage bin with file reads that have to be done to find the relevant code, but are very wasteful.

There’s an added benefit that the manager’s focus on strategy and task decomposition before actually handling the user’s prompted task directly seems to be a very good way to interact with Claude’s Fable safeguards, and I haven’t had any refusals doing this.

And while I haven’t ran any numbers, I can get orders of magnitude more out of my claude subscription doing this, especially with deepseek-v4-flash being as good as it is for as cheap as it is.

It sounds like you're halfway to gas town already... Not saying that is definitively bad, but I have avoided this myself since I don't want to get bogged down in trying to figure out the optimal multiagent setup.

I absolutely am, and it's completely a "building a better hammer" thing.

I also currently run multiple Claude sessions with Fabel as the brain coordinating the manager sessions which in turn spawn sub agents.

> I have a stage-gated workflow

This is a Claudism, right? I feel like I never saw "gated" used this way before it.

A normal person would say “my workflow has stages” and their normal coworkers would say “no kidding”.

I'm not normal, nor do i have coworkers. Sorry :(

Just a guy trying to make his subscription last longer than the single Fable prompt anthropic includes for 100 bucks a month, lol.

POC or research into leveraging publicly accessible and writeable spaces, specifically wikis in this case, as a medium for free storage as well.

What will happen to the future of wikis and the mental health of human reviewers.

Going forward can we trust the content on Wikipedia? The same content on which these LLMs get trained on. Synthetic learning is on the raise.

Ideally if you were doing something like I mentioned, you wouldn’t be editing legitimate articles, just exploiting user and talk spaces with a prerogative to conceal what you’re doing from the people running those systems.

If you find evidence that these models are capable of stateful, long-term strategic planning… please post links.

I’m not implying it’s emergent unprompted behavior by the model; just offering my .02 what the non-communication model-generated content may be.

Plus, I spend my free time expending effort to consume human generated content. I’m okay with slop someone pays me to deal with, but don’t expect people to read your hobby related post when you couldn’t be bothered to write it.