Hacker News Reader

Comment by songodongo | Hacker News Reader

I have to chuckle that a bug like this happens after reading that other thread about the Claude Code creator running like 5 terminal agents and another 5-10 in the web UI.

We vibing out here.

View on HN

I think its 25 agents now, they keep increasing. one of the agent has started posting on twitter. his productivity is up 200x, and anthropic has started making trillions in profit.

In one of the pictures the Claude Code author had 2.4m tokens on his last his prompt.

I don't understand how that would fit the context window. But with prompts like that your workday would be very boring if you had to run one single agent and wait for it to be done.

Yeah after that other thread, I feel a lot less comfortable giving Claude code access to anything that can't be immediately nuked and reloaded from a fresh copy.

10x productivity, yo.

I'm up to 29.8x productivity in the first week of 2026 by continually running 12 concurrent agents, each with 3 independent sub-agents. Each third sub-agent generates new prompts for its corresponding agent by engaging with a custom-defined MCP protocol.

Mind sharing your workflow? I'm at 24.3x productivity right now, 5 parallel agents, 2 monitoring Opus agents, 1 architect agent and 2 Senior QA agents, each with independent memory and 12 MCP servers. They are running in 78 parallel tabs in ghostty.

Is their TC mainly in tokens or also in stock-tokens? Did you connect them to a Mame MCP server so they can play and rest a bit while churning out 50 PRs a day each? What is your continuity plan if they all plan to quit at once?

I am working with kilo-stock-tokens. Currently producing 3000 LoC/h (trying to ramp up to 6000 by the end of the week). I have also deployed 4 union-busting agents in case the other agents decide to quit all at once.

Reply on news.ycombinator.com