Google Product Quality Issues

Complaints about Gemini app UX problems including context loss, Russian propaganda sources, switching languages mid-sentence, document upload failures, and poor integration compared to ChatGPT

Users widely dismiss Gemini as a "benchmark-optimized" disappointment that fails to match the real-world utility and instruction-following capabilities of competitors like ChatGPT and Claude. Frequent complaints highlight bizarre technical failures—such as the model switching to Chinese mid-sentence or citing Russian propaganda—alongside a "broken" UX plagued by document upload errors and massive RAM consumption. While a small minority appreciates its speed and bundled pricing, most contributors describe the product as a "shambles" that frequently loses context and ignores explicit user commands. Ultimately, the consensus suggests that while Google’s underlying tech may be impressive, the actual user experience is marred by technical inconsistency and poor integration into professional workflows.

View on HN · Topics

Can you give an example of smartness where Gemini is better than the other 2? I have found Gemini 3 pro the opposite of smartness on the tasks I gave him (evaluation, extraction, copy writing, judging, synthesising ) with gpt 5.2 xhigh first and opus 4.5/4.6 second. Not to mention it likes to hallucinate quite a bit .

View on HN · Topics

Strange, because I could not for the life of me get Gemini 3 to follow my instructions the other day to work through an example with a table, Claude got it first try.

View on HN · Topics

I've been surprised how difficult it is for LLMs to simply answer "I don't know."

It also seems oddly difficult for them to 'right-size' the length and depth of their answers based on prior context. I either have to give it a fixed length limit or put up with exhaustive answers.

View on HN · Topics

Indeed that answer is awesome. Much better than Gemini 2.5 pro which invented a 16 kilovolt diode which it just hoped would be marked "UM16".

View on HN · Topics

Am I the only one that can’t find Gemini useful except if you want something cheap? I don’t get what was the whole code red about or all that PR. To me I see no reason to use Gemini instead of of GPT and Anthropic combo. I should add that I’ve tried it as chat bot, coding through copilot and also as part of a multi model prompt generation.

Gemini was always the worst by a big margin. I see some people saying it is smarter but it doesn’t seem smart at all.

View on HN · Topics

It's garbage really, cannot get how they get so high in benchmarks.

View on HN · Topics

I find the quality is not consistent at all and of all the LLMs I use Gemini is the one most likely to just verge off and ignore my instructions.

View on HN · Topics

Same, as far as I am concerned, Gemini is optimized for benchmarks.

I mean last week it insisted suddenly on two consecutive prompts that my code was in python. It was in rust.

View on HN · Topics

Their models might be impressive, but their products absolutely suck donkey balls. I’ve given Gemini web/cli two months and ran away back to ChatGPT. Seriously, it would just COMPLETELY forget context mid dialog. When asked about improving air quality it just gave me a list of (mediocre) air purifiers without asking for any context whatsoever, and I can list thousands of conversations like that. Shopping or comparing options is just nonexistent.
It uses Russian propaganda sources for answers and switches to Chinese mid sentence (!), while explaining some generic Python functionality.
It’s an embarrassment and I don’t know how they justify 20 euro price tag on it.

View on HN · Topics

I agree. On top of that, in true Google style, basic things just don't work.

Any time I upload an attachment, it just fails with something vague like "couldn't process file". Whether that's a simple .MD or .txt with less than 100 lines or a PDF. I tried making a gem today. It just wouldn't let me save it, with some vague error too.

I also tried having it read and write stuff to "my stuff" and Google drive. But it would consistently write but not be able to read from it again. Or would read one file from Google drive and ignore everything else.

Their models are seriously impressive. But as usual Google sucks at making them work well in real products.

View on HN · Topics

I don't find that at all. At work, we've no access to the API, so we have to force feed a dozen (or more) documents, code and instruction prompts through the web interface upload interface. The only failures I've ever had in well over 300 sessions were due to connectivity issues, not interface failures.

Context window blowouts? All the time, but never document upload failures.

View on HN · Topics

I'm talking about Gemini in the app and on the web. As well as AI studio. At work we go through Copilot, but there the agentic mode with Gemini isn't the best either.

View on HN · Topics

Honestly this is as Google product as you can get. Prizes for some, beatings for others.

View on HN · Topics

Antigravity is an embarrassment.

The models feel terrible, somehow, like they're being fed terrible system prompts.

Plus the damn thing kept crashing and asking me to "restart it". What?!

At least Kiro does what it says on the tin.

View on HN · Topics

How can the models be impressive if they switch to Chinese mid-sentence? I've observed those bizarre bugs too. Even GPT-3 didn't have those. Maybe GPT-2 did. It's actually impressive that they managed to botch it so badly.

Google is great at some things, but this isn't it.

View on HN · Topics

It's so capable at some things, and others are garbage.
I uploaded a photo of some words for a spelling bee and asked it to quiz my kid on the words. The first word it asked, wasn't on the list. After multiple attempts to get it to start asking only the words in the uploaded pic, it did, and then would get the spellings wrong in the Q&A. I gave up.

View on HN · Topics

100x agree. It gives inconsistent edits, would regularly try to perform things I explicitly command to not.

View on HN · Topics

Agreed on the product. I can't make Gemini read my emails on GMail. One day it says it doesn't have access, the other day it says Query unsuccessful.
Claude Desktop has no problem reaching to GMail, on the other hand :)

View on HN · Topics

Sadly true.

It is also one of the worst models to have a sort of ongoing conversation with.

View on HN · Topics

And it gives incorrect answers about itself and google’s services all the time. It kept pointing me to nonexistent ui elements. At least it apologizes profusely! ffs

View on HN · Topics

I don't have any of these issues with Gemini. I use it heavily everyday. A few glitches here and there, but it's been enormously productive for me. Far more so then chatgpt, which I find mostly useless.

View on HN · Topics

Just not search. The search product has pretty much become useless over the past 3 years and the AI answers often will get just to the level of 5 years ago. This creates a sense that that things are better - but really it’s just become impossible to get reliable information from an avenue that used to work very well.

I don’t think this is intentional, but I think they stopped fighting SEO entirely to focus on AI. Recipes are the best example - completely gutted and almost all receive sites (therefore the entire search page) run by the same company. I didn’t realize how utterly consolidated huge portions of information on the internet was until every recipe site about 3 months ago simultaneously implemented the same anti-Adblock.

View on HN · Topics

The search product become useless on a particular day of 2019 as discussed on HN News some time ago:

https://news.ycombinator.com/item?id=40133976

View on HN · Topics

Wartime Google gave us Google+. Wartime Google is still bumbling, and despite OpenAI's numerous missteps, I don't think it has to worry about Google hurting its business yet.

View on HN · Topics

Don't let the benchmarks fool you. Gemini models are completely useless not matter how smart they are. Google still hasn't figure out tool calling and making the model follow instructions. They seem to only care about benchmarking and being the most intelligent model on paper. This has been a problem of Gemini since 1.0 and they still haven't fixed it.

Also the worst model in terms of hallucinations.

View on HN · Topics

Are you using Gemini model itself or using the Gemini App? They are different.

View on HN · Topics

Both

View on HN · Topics

Those black nazis in the first image model were a cause of inside trading.

View on HN · Topics

I'm leery to use a Google product in light of their history of discontinuing services. It'd have to be significantly better than a similar product from a committed competitor.

View on HN · Topics

Trick? Lol not a chance. Alphabet is a pure play tech firm that has to produce products to make the tech accessible. They really lack in the latter and this is visible when you see the interactions of their VP's. Luckily for them, if you start to create enough of a lead with the tech, you get many chances to sort out the product stuff.

View on HN · Topics

Google is still behind the largest models I'd say, in real world utility. Gemini 3 Pro still has many issues.

View on HN · Topics

Gemini's UX (and of course privacy cred as with anything Google) is the worst of all the AI apps. In the eyes of the Common Man, it's UI that will win out, and ChatGPT's is still the best.

View on HN · Topics

They don't even let you have multiple chats if you disable their "App Activity" or whatever (wtf is with that ass naming? they don't even have a "Privacy" section in their settings the last time I checked)

and when I swap back into the Gemini app on my iPhone after a minute or so the chat disappears. and other weird passive-aggressive take-my-toys-away behavior if you don't bare your body and soul to Googlezebub.

ChatGPT and Grok work so much better without accounts or with high privacy settings.

View on HN · Topics

> Gemini's UX ... is the worst of all the AI apps

Been using Gemini + OpenCode for the past couple weeks.

Suddenly, I get a "you need a Gemini Access Code license" error but when you go to the project page there is no mention of this or how to get the license.

You really feel the "We're the phone company and we don't care. Why? Because we don't have to." [0] when you use these Google products.

PS for those that don't get the reference: US phone companies in the 1970s had a monopoly on local and long distance phone service. Similar to Google for search/ads (really a "near" monopoly but close enough).

0 - https://vimeo.com/355556831

View on HN · Topics

I find Gemini's web page much snappier to use than ChatGPT - I've largely swapped to it for most things except more agentic tasks.

View on HN · Topics

You mean AI Studio or something like that, right? Because I can't see a problem with Google's standard chat interface. All other AI offerings are confusing both regarding their intended use and their UX, though, I have to concur with that.

View on HN · Topics

The lack of "projects" alone makes their chat interface really unpleasant compared to ChatGPT and Claude.

View on HN · Topics

AI Studio is also significantly improved as of yesterday.

View on HN · Topics

No projects, completely forgets context mid dialog, mediocre responses even on thinking, research got kneecapped somehow and is completely uses now, uses propaganda Russian videos as the search material (what’s wrong with you, Google?), janky on mobile, consumes GIGABYTES of RAM on web (seriously, what the fuck?). Left a couple of tabs over night, Mac is almost complete frozen because 10 tabs consumed 8 GBs of RAM doing nothing. It’s a complete joke.

View on HN · Topics

Gemini is completely unusable in VS Code.
It's rated 2/5 stars, pathetic: https://marketplace.visualstudio.com/items?itemName=Google.g...

Requests regularly time out, the whole window freezes, it gets stuck in schizophrenic loops, edits cannot be reverted and more.

It doesn't even come close to Claude or ChatGPT.

View on HN · Topics

Have you tried providing multiple pages at a time to the model? It might do better transcription as it have bigger context to work with.

View on HN · Topics

Gemini 3 long context is not good as Gemini 2.5

View on HN · Topics

I'd rather say it has a mind of its own; it does things its way. But I have not tested this model, so they might have improved its instruction following.

View on HN · Topics

Too bad we can’t use it. Whenever Google releases something, I can never seem to use it in their coding cli product.

View on HN · Topics

I do like google models (and I pay for them), but the lack of competitive agent is a major flaw in Google's offering. It is simply not good enough in comparison to claude code. I wish they put some effort there (as I don't want to pay two subscriptions to both google and anthropic)

View on HN · Topics

Is this not yet available for workspace users? I clicked on the Upgrade to Google AI Ultra button on the Gemini app and the page it takes me to still shows Gemini 2.5 Deep Think as an added feature. Wondering if that's just outdated info

View on HN · Topics

Gemini was awesome and now it’s garbage.

It’s impossible for it to do anything but cut code down, drop features, lose stuff and give you less than the code you put in.

It’s puzzling because it spent months at the head of the pack now I don’t use it at all because why do I want any of those things when I’m doing development.

I’m a paid subscriber but there’s no point any more I’ll spend the money on Claude 4.6 instead.

View on HN · Topics

I never found it useful for code. It produced garbage littered with gigantic comments.

Me: Remove comments

Literally Gemini: // Comments were removed

View on HN · Topics

I wish they would unleash it on the Google Cloud console. Whatever version of Gemini they offer in the sidebar when I log in is terrible .

View on HN · Topics

Does anyone actually use Gemini 3 now? I cant stand its sleek salesy way of introduction, and it doesnt hold to instructions hard – makes it unapplicable for MECE breakdowns or for writing.

View on HN · Topics

It indeed departs from instructions pretty regularly. But I find it very useful and for the price it beats the world.

"The price" is the marginal price I am paying on top of my existing Google 1, YouTube Premium, and Google Fi subs, so basically nothing on the margin.

Summarizer