LLMs are smart but not yet 'sharp': a new qualitative lens on model progress
jmugan · x · 2026-09-19
jmugan observes that we call smart people "sharp," and LLMs are now smart enough that their dullness is visible: they can instantly access all human knowledge yet often miss exactly what you mean, giving imprecise answers. He frames this as good news — sharpness resists quantification, but it offers a new qualitative way to measure model progress.
Related event: Researchers say LLMs are smart but not 'sharp' enough(2 posts)→
More from Models
- Alibaba's Qwen3.8-LiveTranslate does real-time speech translation with 2.3s lag and speaker separation — xiaohu · 2026-09-19
- Alibaba's Qwen3.8-LiveTranslate cuts speech translation lag to 2.3s, adds speaker separation — xiaohu · 2026-09-19
- Are quantized small models the real sweet spot for local AI? — sunychoudhary · 2026-09-19
- "All major LLMs read as spiritually male" — an observation sparking debate — dioscuri · 2026-09-19
- "Most people just want an endpoint": GLiNER2, open source for a year, still overlooked — TheMoonMidas · 2026-09-19
- Jev vs GPT-6 Astra: testing model-controlled robot arms in MuJoCo — const_reborn · 2026-09-19