@filicroval: gemini 3.8 flash might be the fastest model i've ever used it only took 5 minutes to generate this Voxel Lighthouse via…

X AI KOLs Following Models

Summary

A user praises Gemini 3.8 Flash for its exceptional speed in generating a Voxel Lighthouse in just 5 minutes and compares its performance to Hy4 Preview in one-shot prompting.

gemini 3.8 flash might be the fastest model i've ever used it only took 5 minutes to generate this Voxel Lighthouse via Hermes i've tested many model for agentic usage and nothing comes close to this speed. i didn't even have time to grab my coffee and the output isn't even bad, it's genuinely good.
Original Article
View Cached Full Text

Cached at: 09/03/26, 02:03 AM

gemini 3.8 flash might be the fastest model i’ve ever used

it only took 5 minutes to generate this Voxel Lighthouse via Hermes

i’ve tested many model for agentic usage and nothing comes close to this speed. i didn’t even have time to grab my coffee

and the output isn’t even bad, it’s genuinely good.

filipe (@filicroval): hy4 preview is definitely not a model we should sleep on

same prompt for each model, one-shot.

i would have expected the gap between both to be bigger but Hy4 Preview still comes close (it’s twice the size but still). very huge leap since Hy3

curious which one you’d pick

Similar Articles

Gemini 3.1 Flash-Lite

Product Hunt

Google releases Gemini 3.1 Flash-Lite, a lightweight version of the Gemini model designed for high-volume AI pipelines.

Gemini 3 Flash: frontier intelligence built for speed

Google DeepMind Blog

Google has released Gemini 3 Flash, a fast, cost-effective AI model that combines Pro-grade reasoning with Flash-level speed for tasks like coding, complex analysis, and agentic workflows.

Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

Hacker News Top

Google introduces Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber models, offering improved token efficiency, lower latency, and better performance for agentic workflows, with 3.6 Flash reducing output token usage by 17% and showing gains in coding and knowledge tasks.