Editor runs paper through ChatGPT after rejection; AI finds real errors missed by reviewer
skdh · x · 2026-08-15
A researcher shared an experience where, after a paper was rejected due to an unproductive back-and-forth with a referee making repeated mistakes, the editor ran the manuscript through ChatGPT. Unlike the human reviewer, the AI uncovered actual errors in the paper and provided genuinely useful feedback. The author concluded that a real-time chat with an LLM is preferable to months-long back-and-forth with human reviewers.
More from Research
- Google-led paper uses sequential auctions to organize decentralized LLM agent workflows — _onionesque · 2026-10-16
- How meloform works: WASM pitch detection plus differentiable circuits learning 1,022 sine coefficients — henloitsjoyce · 2026-10-16
- Since OpenAI's math release, GitHub contributors keep driving down the integer-multiplication kappa — xennygrimmato_ · 2026-10-16
- RFdiffusion3 debuts in Science: generative AI designs proteins and nucleic acids atom by atom — AllThingsApx · 2026-10-16
- New Science report urges NSF to run experiments on science funding reform — alexeyguzey · 2026-10-16
- AI Turns Scrap Impurities into Useful Ingredients for Stronger Recycled Iron — webthing01 · 2026-10-16