User Blasts Gemini for Failing to Find Its Own Info, Alleges Constant Nerfing
umeshonai · x · 2026-10-20
An X user publicly calls out @GeminiApp and @googleaidevs, complaining that Gemini cannot even retrieve information about itself, let alone handle other tasks, and accuses Google of continually nerfing the model. The post references "Gemini 4 Argon" as something that was supposed to solve the hardest problems, and tags Google executive Koray Kavukcuoglu. It is user feedback on Gemini's real-world behavior without concrete reproduction details.
More from Models
- PretrainGym pits frontier agents on pretraining data curation: Kimi K3 wins at 1.042 — xeophon · 2026-10-20
- SlideOn model card details SAE pretraining and Matryoshka sparse training recipe — tomaarsen · 2026-10-20
- LightOn ships 16.3M training pairs and full code alongside SlideOn models — tomaarsen · 2026-10-20
- SlideOn lands in sentence-transformers with one-line SparseEncoder loading — tomaarsen · 2026-10-20
- mSlideOn handles cross-lingual retrieval with raw dot-product scoring — tomaarsen · 2026-10-20
- mSlideOn tops MTEB Code at 74.78 nDCG, beating dense and late-interaction models — tomaarsen · 2026-10-20