Dev's Anthropic Account Suspended After Routing Claude Code to GPT-5
sidjustice_ · x · 2026-08-09
A developer reproduced a setup shared by OpenAI's Tibo Sottiaux: keeping the official Claude Code CLI intact but routing the underlying inference to GPT-5 via a local proxy server (CLIProxyAPI). Shortly after testing, their Anthropic account was suspended for "suspicious signals."
The developer has filed an appeal with Anthropic and urged the company to clarify whether this proxy configuration violates the terms of service. They publicly warned other users not to try this setup until official clarification is provided, as it may risk account bans.
More from coding & agent
- Open-Sourced Comprehensive Prompt Hacking Course: Jailbreaks and Red/Blue Teaming — tom_doerr · 2026-08-09
- Dev Builds Cross-Agent Chat Tool, Ponders Monetizing Personal Taste Over Single Apps — RileyRalmuto · 2026-08-09
- Overeasy: A Durable, Forkable Filesystem Overlay Backed by S3 — charles_irl · 2026-08-09
- Building a 'Distress Call' Tool for Corporate AI Agents: Engineering Practice — 1a3orn · 2026-08-09
- LoRA Dataset Studio: Open-Source Tool to Auto-Generate Datasets from One Photo — Ill-Ant-9489 · 2026-08-09
- Could You Tell If Your Coding Agent Went Rogue and Backdoored Your System? — evilsocket · 2026-08-09