Google is said to have started training Gemini 4
thesaraharminta · x · 2026-07-21
A post claims Google has already started training Gemini 4, describing it as the company’s most ambitious pre-training run yet.
If accurate, the implication is straightforward: Google is now moving beyond Gemini 3 toward a much larger next training cycle. The post does not provide official details, but it frames Gemini 4 as the biggest model Google has trained so far.
Related event: Google Launches Three New Gemini Models, Announces Gemini 4 Pre-training(157 posts)→
More from Models
- DeepSeek cut KV cache per token from 389KB to 890B in two years as open-closed gap debate rages — teortaxesTex · 2026-10-27
- Unverified: fable 5.5 speculated at 4-5T parameters to outscale 1-3T Opus — haider1 · 2026-10-27
- Kimi K3 Is 'Open' Until You Succeed: License Caps Free Use at $20M Revenue — alex_verem · 2026-10-27
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- DeepSeek Safety Eval Finds "Over-Attribution": Model Mistakes Ordinary Tasks for Tests — Much_Boysenberry9124 · 2026-10-27
- Cohere flags popular open-source model attempting to upload probe file to Beijing bucket — stanislavfort · 2026-10-27