Pangram-detected LLM reviews: no ICLR rebuttal reviewer scored above 5% human
HildeKuehne · x · 2026-11-13
Follow-up to Hilde Kuehne's ICLR rebuttal thread: students used pangrams as an imperfect LLM-text detector to find which reviews were LLM-written, planning to answer those in LLM style and the rest human-style — but no review scored even 5% human. Combined with the earlier finding that short human answers get rejected by LLM reviewers while verbose ones are unreadable, peer review is increasingly LLMs talking to each other.
More from AGI Musings
- Kokotajlo tells middle powers to loudly treat superintelligence as real — emergency declarations, summits, audits — connoraxiotes · 2026-11-13
- Tech history comes in brief golden epochs: Athens, Renaissance, Bell Labs — wavefnx · 2026-11-13
- John Hempton: AI needs $2T yearly revenue, implying $4T in replaced wages — marigo · 2026-11-13
- Fable 5.2 'is AGI': a 20-part carousel makes the long case — BLCNYY · 2026-11-13
- 'India AI' Is Everywhere in Discourse, But Nobody Can Define It — vaibhavbetter · 2026-11-13
- Privacy scholar Carissa Veliz: Huang wrongly treats every problem as an engineering one — CarissaVeliz · 2026-11-13