Researcher Breaks Qwen 2.5 via Endless Gaslighting, Forced Off arXiv by Endorsement Rule
IndraVahan · x · 2026-10-11
A researcher spent the weekend endlessly gaslighting Qwen 2.5 until its behavior collapsed, documented the steps in a paper for arXiv — only to hit the endorsement requirement on cs.CL and publish on ResearchGate instead. A look at both model-break experiments and arXiv's submission barriers.
More from Models
- JevBench creator explains why open and API models get separate leaderboards: fairness — airesearch12 · 2026-10-11
- Codebase test: Telnyx-hosted GLM runs 9% cheaper, 5% faster than OpenAI — SucceededMind · 2026-10-11
- Nous Research launches stealth coding and agentic reasoning model, free for limited time — Teknium · 2026-10-11
- I published 50,000 fake stats and ChatGPT still cites them, earning 10k+ AI sessions — metehan777 · 2026-10-11
- Haiku fails 15 of 17 agent runs on output format, deemed no upgrade over Luna — zeeg · 2026-10-11
- Users report Astra performance sharply degraded in recent days, images too — pwlot · 2026-10-11