I’ve noticed that Gemini Flash 3.5/3.6—even on the “High” setting of the “Antigravity” version—gets basic things wrong compared to Gemini Pro 3.1. I don’t know if they tried to copy the style of DeepSeek V4 Flash, but honestly, it’s behaving in a very limited way; it makes mistakes on simple tasks. …

I find myself both agreeing and disagreeing with you. Having frequently approached programming through the Antigravity IDE—which is rather chaotic and demands strict discipline—as well as the Gemini CLI and several other platforms, I have observed that while these models are remarkably swift, they d…

Try using Conductor or Superpowers. I think your problem is that you don’t know how to set up a product. [image] GitHub - gemini-cli-extensions/conductor: A plugin for AI coding agents (Antigravity, Claude... A plugin for AI coding agents (Antigravity, Claude Code) enabling Spec-…

I agree with my colleague’s analysis: this model is clearly inferior to previous Gemini iterations. I can’t speak for other AI models since I’m not as familiar with them, but code generation has definitely taken a step backward. The model struggles with basic reasoning and just fails to grasp instru…

100% agree i put out a youtube video about this yesterday. The biggest worry is that when I want to make a major architectural change and as part of my rules it has to give me options. When I show Claude or Perplexity the options 100% of the time they have told me not to use any of the options. The …

Ok, nvm, there is something weird with Gemini 3.6 Flash; it is super inconsistent. Sometimes it works great, but there are times where it skips whole steps. I think they optimized it too much. It feels exactly like when you work with local models and they start to lie to you. Edit: In this example …

Yes, I know how to use the product, that’s not the question… but I appreciate the help

It is a model that is inferior…I Test several models open and closed and local, this one is certainly worse than Gemini

3.1 ask for more tokens but he tends to respond better and when he makes a mistake he notices and tries to correct but he doesn’t insist on continuing to make mistakes, 3.6 it seems the context is fixed in his mind (his attention is kind of …),It goes into a silly loop, it seems to me that they tri…

EXACTLY, it is very … in simple language, the product is really weak, it looks like a distillation of FLASH V4, you know, because I know that because I use opencode with v4 flash for free via openrouter and opencode zen and the same way of acting and thinking I can’t say that it is improved Distill …

I will just drop this here [image] read more in my post: [image] Flash 3.6 Is WORSE than 3.5 Google Antigravity After some similar experiences, I use 3.6 Flash only for some simple question & answer, not for Agent coding. 3.5 is much better in this regard i…

The 3.6 Flash model... it's weak at coding

Google Antigravity

Gabriel_Nilo July 30, 2026, 2:59pm 12

I will just drop this here

Topic		Replies	Views
Flash 3.6 Is WORSE than 3.5 Google Antigravity feedback , models	7	517	August 6, 2026
The Flash 3.6 model is worse than the 3.5 Google Antigravity models	7	482	July 30, 2026
[Feedback] Significant Quality Degradation in Gemini 3.6 Flash Model (Code Modification Failures) Google Antigravity feedback	1	316	August 8, 2026
Why even Google is making Gemini? Google Antigravity feedback	1	183	July 22, 2026
Gemini 3 Flash and Gemini 3.1 Pro (High) are so bad after your last update Google Antigravity gemini-3	7	1133	July 30, 2026

The 3.6 Flash model... it's weak at coding

Related topics