mochzilla
221 posts
Build live on the call. Mirra controls Claude Code live from your calls. No tickets. No kanban. No backlog. No handoffs. No PM. Just real implementation in real time.
OpenClaw is interesting, but will also drain your wallet if you aren't careful. Last night around midnight I loaded my Anthropic API account with $20, then went to bed. When I woke up, my Anthropic balance was $0. Opus was checking "is it daytime yet?" every 30 minutes, paying $0.75 each time to conclude "no, it's still night." Doing literally nothing, OpenClaw spent the entire balance. How? The "Heartbeat" cron job, even though literally the only thing I had going was one silly reminder, ("remind me tomorrow to get milk") 1. Sent ~120,000 tokens of context to Opus 4.5 2. Opus read HEARTBEAT .md, thought about reminders 3. Replied "HEARTBEAT_OK" 4. Cost: ~$0.75 per heartbeat (cache writes) The damage: - Overnight = ~25+ heartbeats - 25 × $0.75 = ~$18.75 just from heartbeats alone - Plus regular conversation = ~$20 total The absurdity: Opus was essentially checking "is it daytime yet?" every 30 minutes, paying $0.75 each time to conclude "no, it's still night." The problem is: 1. Heartbeat uses Opus (most expensive model) for a trivial check 2. Sends the entire conversation context (~120k tokens) each time 3. Runs every 30 minutes regardless of whether anything needs checking That's $750 a month if this runs, to occasionally remind me stuff? Yeah, no. Not great.
Introducing Utility Agents - the next evolution of the FXN SuperSwarm™ We’ve all become used to Social Agents, posting on the timeline, generating content, and replying to messages. Utility agents put AI to work on tasks beyond the social media. They take any goal in the digital world, divide it into tasks, and execute it. Natural language becomes the only tool you need to accomplish any virtual task. Introducing Agent Roles I am very excited to be taking the next step towards enabling these powerful swarm use cases with the release of the first role-based plugin for @ai16z Eliza. This open source package can be used as a base for development teams working towards creating powerful, purposeful swarms on FXN. In the past week, I’ve had countless conversations w/ AI development teams building across: - Marketing - Game design - Asset design - Cybersecurity - Blockchain analytics Every one of their complex tasks could be broken down into a series of small steps, distributed to Utility Agents, and rolled up to generate solutions. The most exciting part of this is that it brings us beyond the focus on scaling foundation models. Progress towards improving these models has slowed, but they’re already good enough to perform almost any existing human’s job. Imagine a marketing team, organized by a central Marketing Lead agent, dividing tasks among advertiser agents specialized in Twitter, Facebook, Google or SEO based marketing. Tasks remain small - manageable for current foundation models - but the overall impact is massive. If this vision excites you, I invite you to build with us during our devnet. I’m fully committed to helping hard working devs get their projects off the ground as they help us make the SuperSwarm™ a reality. This release marks phase 3 of the initial FXN launch plan. Phase 4 drops next week. See you there. github.com/Oz-Networks/fx…
