Timnit Gebru Slams Pangram Claims: Four 'Non-Native English' Datasets Prove Nothing
TuhinChakr · x · 2026-11-18
Timnit Gebru joined the growing controversy over AI text detector Pangram, mocking claims that its "four datasets of non-native English" make it near-infallible. Boosters note researchers attempting fair evaluations on target language varieties get attacked, while Pangram is criticized for not doing them — the fight over detector false positives on non-native writers keeps escalating.
More from Models
- Speculation Swirls That OpenAI's 6.2 Astra Leans on Looping Transformers, Raising Monitorability Concerns — scaling01 · 2026-11-18
- Could a GPT-6.2 Astra + Opus 5.5 fusion fix the model-human interface? — daniel_mac8 · 2026-11-18
- Why the '1-in-10,000' AI Detector False Positive Claim Doesn't Hold Up — torchcompiled · 2026-11-18
- Developer: DeepSeek 4.1 Flash is basically free to run for personal use — rickasaurus · 2026-11-18
- LLM reviewers draw 50% of weaknesses from the appendix vs 8% for humans — plopesresearch · 2026-11-18
- Users ditching Fable 5.2 for Opus 5.5 as rate limits burn too fast — scaling01 · 2026-11-18