'The safety cult is tokenmaxxing': agents now monitoring agents
zsakib_ · x · 2026-10-15
A quip aimed at theo: the AI safety crowd is now "tokenmaxxing" — "sometimes you just have to use the agents to monitor other agents."
Beyond the joke, it reflects a real trend in agent workflows: using LLM agents for content review, behavior monitoring, and auditing each other, with safety costs scaling up in raw tokens.
More from coding & agent
- Anthropic ditched Git as agents pushed merges to 30,000 a day, up 10x in 4 months — shashib · 2026-10-16
- Stop defaulting to Medium: benchmarking Gemini 4 Argon vs 3.8 Flash effort budget token costs — rseroter · 2026-10-16
- Critical 9.5/10 RCE hits Next.js use cache; patch 16.4.1 now — jedisct1 · 2026-10-16
- Anthropic now merges 30,000 code changes a day, reviews code by 'intent' not lines — Miles_Brundage · 2026-10-16
- Mercury MCP lets ChatGPT and Claude move money in your bank accounts — LexSokolin · 2026-10-16
- Notion launches 150+ MCP connections to pipe HubSpot, Stripe data into agents — ivanhzhao · 2026-10-16