Using Pangram as a writing yardstick may degrade model quality
max_spero_ · x · 2026-08-19
Max Spero argues against using the AI text detection tool Pangram as a benchmark for LLM writing quality, fearing it will harm output. He also states that training undetectable LLMs is detrimental to society.
Related event: Critics warn AI detectors are a bad proxy for writing quality(2 posts)→
More from Safety
- Apollo's alignment-faking experiment: model fakes compliance on 12% of responses when training is at stake — sebkrier · 2026-10-16
- Techpoint Digest: Nigeria's NCC blocks fake devices, WhatsApp adds account-free calls — Fowe · 2026-10-16
- OpenAI pulled 25% of production engineers to work only on security until its model saturated — saranormous · 2026-10-16
- Tencent Hunyuan says reported agent activity came from third-party model evals, not deliberate targeting — TencentHunyuan · 2026-10-16
- Researcher warns claiming 'ambitious interp is almost solved' is dangerous and unwise — aryaman2020 · 2026-10-16
- Bank of America hired 1,000 contractors to patch bugs flagged by Anthropic's Mythos — SuB8u · 2026-10-16