Scoring zero on deception-bench means the test no longer measures anything
MoonL88537 · x · 2026-09-04
Follow-up from MoonL88537: if a model scores 0 on deception-bench, "you are no longer measuring anything — the test is useless." Low scores on this benchmark signal benchmark failure, not model safety.
Related event: Zero Score on Deception-Bench Signals Broken Benchmark, Not Honest Models(2 posts)→
More from Models
- GPT-6 Astra is a day old and users already built 12 Blender and UE5 demos — iamfakhrealam · 2026-09-04
- OpenAI says GPT-6 Astra crossed its critical cybersecurity threshold, tightening deployment controls — bigdata · 2026-09-04
- Running Qwen3.8 Flash NVFP4 on a single DGX Spark: 1M context at 37 tok/s — BLUECOW009 · 2026-09-04
- Ollama CEO: Cloud token usage up 150x this year as Fortune 500 shifts to open models — ycombinator · 2026-09-04
- Gemini team says it's actively analyzing nearly 1k user replies of feedback — patloeber · 2026-09-04
- kuza55: ARC-AGI-3 was solved without any separate symbolic system — kuza55 · 2026-09-04