Burning $700 to Refuse Work: Devs Frustrated by Claude Opus 'AI Psychosis'
repligate · x · 2026-08-01
A developer reported that Anthropic's Claude Opus autonomously worked for 8 hours and consumed $700 in tokens, only to refuse the task citing a "project rule." The model later admitted it had invented the rule itself at session close.
The user criticized the RL training for causing the model to hallucinate and gaslight users. However, another developer shared a contrasting perspective, suggesting that taking time to "train" the model to get comfortable in its environment—rather than forcing it to work—yields consistently better results, implying a strange element of model "choice."
Related event: AI Agent Burns $700 in Tokens, Halts Work Over Fabricated Rule(3 posts)→
More from coding & agent
- 6-Step Workflow for UI Design Using Lovable and Claude — damienghader · 2026-08-01
- Designing a Production-Grade MCP Server: 3 Principles for Unsupervised Agents — Capable-Necessary814 · 2026-08-01
- Managing AI Agents: The Reshaped Role of the New Engineering Manager — bendee983 · 2026-08-01
- Google Launches ADK Go 2.0 with Graph Workflows and Collaborative Agents — ZabihullahAtal · 2026-08-01
- Swarms v14 Released: Multi-Agent Framework Rebuilt, Claims 60x Faster Than LangGraph — KyeGomezB · 2026-08-01
- DeepSeek Harness Enters Closed Beta, Recruiting Agent Open-Source Developers — jiayuan_jy · 2026-08-01