theootzen··on Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find outWhich sandboxes do you yourself use to run those agents? And how did you choose this provider?
theootzen··on We tested 20 LLMs for ideological bias, revealing distinct alignmentsVery interesting. Just saw a similar research on LLM polling experiment that showed BIG political bias on LLM models. Article link: https://pollished.tech/article/llm-political-bias?lang=en