AI tools · ai assistant
Google Gemini
Recommended for everyday questions, image and handwriting understanding, and coding or scripting help, but many report confidently invented facts and dislike it being pushed into every Google product.
Summarized from 6792 comments.
Recommended for everyday questions, image and handwriting understanding, and coding or scripting help, but many report confidently invented facts and dislike it being pushed into every Google product.
- recommend
- 2195
- criticize
- 2236
- months recommended
- 13 of 13
- median owned, 98 owners said
- 0.5 years
Why people love it
Answers everyday questions well · 5
Someone who can't afford to get ripped off by a mechanic... has a decent chance of solving simple car problems instantly on their own by asking ChatGPT or Gemini.
Feb 2026 · commentGemini was able to help me confirm with and provide resources from specialists about this because the average psychiatrist knows nothing about this.
Jun 2026 · commentGemini's integration is, I think, absolutely awesome - it's completely changing the way I interact with the concept of googling and finding answers
Jul 2026 · commentStrong multimodal and image understanding · 4
Gemini's multimodal understanding, things like identifying what a plant is, normal user use cases (other than chatting), integration with other tools, is much better.
Apr 2026 · commentI used Gemini to decode and transcribe an old (and well known) cursive hand written mail. I couldn't read it at all. It managed to do this in a few seconds.
Nov 2025 · commentGemini is still excellent at simple, short-term, and even multimodal tasks, but it is not well-suited for long-term planning scenarios for AI agents.
Jul 2026 · commentHandy for scripts and code · 4
I find that I can ask Gemini to blurt out an XSLT implementation of my requirements given a snippet of example doc, and I have used this to good effect in some web scrapers/robots.
Nov 2025 · commentI find Gemini to be quite good / acceptable at code review, design, and design review, but it's notably far behind Claude Code for implementation.
May 2026 · commentI asked Google Gemini to write me an AutoHotkey script to do the Caps Lock / Shift Caps Lock for layout 1 or 2 respectively, it works well!
Jun 2026 · commentReliable structured output via API · 3
the gemini cli agent with gemini 2 half the time writes its own tool call parameters incorrectly
Jan 2026 · commentGemini 1.5 Pro did a much better job across all of our language pairs, it wasn't close
Apr 2026 · commentI have pushed Gemini 2.5 Pro further than I thought possible when it comes to ridiculously over complicated (by necessity) structured output.
Dec 2025 · comment
What people warn about
Hallucinates facts and sources · 6
Earlier today I asked Gemini Pro to find information on a person's death that was turning up nothing for me otherwise, and it just imagined finding verbatim Obituary quotes in every source
Dec 2025 · commentthere is no album called "Wild Kingdom" by an artist named Deadbeat, and while Hassan does appear on "Red Hot + Cool" it is on a differently named track written by himself
Nov 2025 · commentGemini might be wrong all the time and absuredly unreliable for anything that's not consensus or adversorial based, but at least it freaking apologizes
Jul 2026 · commentForced into all Google products · 3
Being able to push Gemini into your face on Gmail, Gdocs, Google Search, Android, Android TV, Android Auto and Pixel devices sure is: Annoying, disruptive and unfair.
Dec 2025 · commentIt is deliberately designed for maximum accidental invocations so the managers and execs behind it can claim the large user numbers in their promo packets.
May 2026 · commentA blast of gmail messages from Google has announced how it's part of everything and given instructions on how to find out the little you can do about it.
Aug 2026 · commentWeak at agentic, long tasks · 3
Gemini is still excellent at simple, short-term, and even multimodal tasks, but it is not well-suited for long-term planning scenarios for AI agents.
Jul 2026 · commentAsking gemini 3 to refactor things or in very narrow things to help was ok, but it was quite bad at getting the general context, and spotting bugs
Apr 2026 · commentIt's stunningly good at reasoning, design, and generating the raw code, but it just falls over a lot when actually trying to get things done
Feb 2026 · commentBuggy apps and settings · 3
Gemini thinks my name is my brother in law's name, and despite explicitly telling it that's not my name + digging through the settings, it still amusingly calls me the wrong name.
May 2026 · commentHaving a "bug" that changes available model options for some small set of Pro users 3 months after launch certainly qualifies as a wtf-are-they-even-doing level of bug
Sep 2026 · commentThe Android and web app is also riddled with bugs, including ones that makes you lose your chat history from the threads if you switch between them, not cool.
Apr 2026 · comment
What hackers pick instead
- ClaudeRecommended for debugging from logs, implementing tricky algorithms and performance tuning, but it makes mistakes on large codebase changes and needs close supervision.5175recommend
- ChatGPTA general-purpose chatbot that people use to research faster, understand health issues, learn topics and draft writing, though it often hallucinates and tells you what you want to hear.2186recommend
- GrokRecommended for fast, concise answers, real-time current events through X, and useful second opinions on code, but critics widely cite Musk-driven political bias and weak safety guardrails.727recommend
- Microsoft CopilotValued for tight Microsoft 365 integration that finds work documents while respecting access permissions; critics dislike Copilot buttons pushed everywhere, confusing branding and made-up links.139recommend
- Claude DesktopPeople recommend it as an approachable home for Claude agents, with connectors, artifacts and parallel sessions; critics call the Electron app slow, buggy and resource-heavy, and dislike its large VM.104recommend
Every quote
The 40 most detailed of 6792 comments. Each links to the original.
Earlier today I asked Gemini Pro to find information on a person's death that was turning up nothing for me otherwise, and it just imagined finding verbatim Obituary quotes in every source
Mixed · Dec 2025 · in “Gut bacteria from amphibians and reptiles achieve tumor elimination in mice”
I find that I can ask Gemini to blurt out an XSLT implementation of my requirements given a snippet of example doc, and I have used this to good effect in some web scrapers/robots.
Recommends · Nov 2025 · in “Google is killing the open web, part 2”
Gemini's multimodal understanding, things like identifying what a plant is, normal user use cases (other than chatting), integration with other tools, is much better.
Recommends · Apr 2026 · in “OpenAI raises $122B”
Being able to push Gemini into your face on Gmail, Gdocs, Google Search, Android, Android TV, Android Auto and Pixel devices sure is: Annoying, disruptive and unfair.
Mixed · Dec 2025 · in “Google, Nvidia, and OpenAI”
It was imprecise, but with some guidance (and by putting together my basic skills with Gemini's vast but unreliable knowledge) I was able to figure out a few things
Mixed · Nov 2025 · in “Show HN: An LLM-Powered Tool to Catch PCB Schematic Mistakes”
Someone who can't afford to get ripped off by a mechanic... has a decent chance of solving simple car problems instantly on their own by asking ChatGPT or Gemini.
Recommends · Feb 2026 · in “U.S. had almost no job growth in 2025”
I used Gemini to decode and transcribe an old (and well known) cursive hand written mail. I couldn't read it at all. It managed to do this in a few seconds.
Recommends · Nov 2025 · in “Tell HN: Mechanical Turk is twenty years old today”
I had Gemini generate a quick explainer on how CGI-based web servers work because I thought it could explain it a little bit more compactly than I could.
Mixed · Oct 2026 · in “What should we tell our students?”
gemini 3 has pretty clearly been trained for this workflow of text output, since it can actually get the right calls in the first shot most of the time
Recommends · Jan 2026 · in “How to Code Claude Code in 200 Lines of Code”
Gemini might be wrong all the time and absuredly unreliable for anything that's not consensus or adversorial based, but at least it freaking apologizes
Mixed · Jul 2026 · in “Societal Impacts: Claude's values across models and languages”
Gemini is still excellent at simple, short-term, and even multimodal tasks, but it is not well-suited for long-term planning scenarios for AI agents.
Mixed · Jul 2026 · in “Ask HN: Did Google give up in the AI Race?”
Gemini was able to help me confirm with and provide resources from specialists about this because the average psychiatrist knows nothing about this.
Recommends · Jun 2026 · in “Encephalitis”
Gemini's integration is, I think, absolutely awesome - it's completely changing the way I interact with the concept of googling and finding answers
Recommends · Jul 2026 · in “Google Discloses $94.1B in SpaceX Stock, Marking 6% Stake”
Gemini is capable of giving good technical advice and step-by-step instructions on clearing issues, but often with a pinch of toxic LSD in the mix
Mixed · Jul 2026 · in “It's not empowering to hand off the details”
Asking gemini 3 to refactor things or in very narrow things to help was ok, but it was quite bad at getting the general context, and spotting bugs
Mixed · Apr 2026 · in “Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving”
I've never ever had Gemini over the API switch languages in translation tasks and that's across more than 10 language pairs and 6 figures of calls
Recommends · Apr 2026 · in “Our eighth generation TPUs: two chips for the agentic era”
I find Gemini to be quite good / acceptable at code review, design, and design review, but it's notably far behind Claude Code for implementation.
Mixed · May 2026 · in “Accelerating Gemma 4: faster inference with multi-token prediction drafters”
Gemini / Claude have both been surprisingly good at understanding my half-assed attempts to put a complicated question into a coherent sentence
Recommends · Jul 2026 · in “LearnVector – Andrew Ng's AI company building one‑to‑one learning experiences”
I have pushed Gemini 2.5 Pro further than I thought possible when it comes to ridiculously over complicated (by necessity) structured output.
Recommends · Dec 2025 · in “All I Want for Xmas Is Your Secrets: LangGrinch Hits LangChain (CVE-2025-68664)”
I find I can usually just drop some images of a MJ style into Gemini and get it to give me a text prompt that works just as well as MJ srefs.
Recommends · Feb 2026 · in “Qwen-Image-2.0: Professional infographics, exquisite photorealism”
It's stunningly good at reasoning, design, and generating the raw code, but it just falls over a lot when actually trying to get things done
Mixed · Feb 2026 · in “Gemini 3.1 Pro”
I asked Google Gemini to write me an AutoHotkey script to do the Caps Lock / Shift Caps Lock for layout 1 or 2 respectively, it works well!
Recommends · Jun 2026 · in “Made a free macOS menu bar app that fixes typing in the wrong keyboard layout”
Gemini works great for answering questions and delivering answers for probably 90%+ of the things that people are going to ask Google for
Recommends · Aug 2026 · in “Google DeepMind CEO Demis Hassabis is stepping down”
Gemini 1.5 Pro did a much better job across all of our language pairs, it wasn't close
Recommends · Apr 2026 · in “Our eighth generation TPUs: two chips for the agentic era”
Gemini thinks my name is my brother in law's name, and despite explicitly telling it that's not my name + digging through the settings, it still amusingly calls me the wrong name.
Criticizes · May 2026 · in “Grok 4.3”
there is no album called "Wild Kingdom" by an artist named Deadbeat, and while Hassan does appear on "Red Hot + Cool" it is on a differently named track written by himself
Criticizes · Nov 2025 · in “Americans no longer see four-year college degrees as worth the cost”
Having a "bug" that changes available model options for some small set of Pro users 3 months after launch certainly qualifies as a wtf-are-they-even-doing level of bug
Criticizes · Sep 2026 · in “Gemini 4 Argon”
The Android and web app is also riddled with bugs, including ones that makes you lose your chat history from the threads if you switch between them, not cool.
Criticizes · Apr 2026 · in “Our eighth generation TPUs: two chips for the agentic era”
it likes to spell Acknowledge as Acknolwedge. And I've run into issues when it's accessing markdown guides, it loses track and hallucinates from time to time
Criticizes · Dec 2025 · in “GPT-5.2”
It is deliberately designed for maximum accidental invocations so the managers and execs behind it can claim the large user numbers in their promo packets.
Criticizes · May 2026 · in “Googlebook: Designed for Gemini Intelligence – Coming Fall 2026 – Googlebook”
A blast of gmail messages from Google has announced how it's part of everything and given instructions on how to find out the little you can do about it.
Criticizes · Aug 2026 · in “Gemini becomes Google's fastest-growing product ever as it hits 1B users”
the gemini cli agent with gemini 2 half the time writes its own tool call parameters incorrectly
Criticizes · Jan 2026 · in “How to Code Claude Code in 200 Lines of Code”
If Gemini is good enough for the majority of people to complete the majority of tasks they want to then market effects and bundling can get an already dominant company like Google to take over the market.
Mixed · Dec 2025 · in “The Walt Disney Company and OpenAI Partner on Sora”
The warnings firing off hours later is obviously awful design, but the warnings are just warnings. The spend caps are something different and Gemini has them at the very least.
Mixed · Apr 2026 · in “€54k spike in 13h from unrestricted Firebase browser key accessing Gemini APIs”
They are just signing a partnership with their biggest competitor and giving them access to their main competitive advantage, the most advanced AI available.
Mixed · Jan 2026 · in “Apple picks Google's Gemini to power Siri”
the fact that the transcript isn't close to an exact match to what was said - and the timestamps are incorrect - means it's very hard to trust the output
Mixed · Nov 2025 · in “Trying out Gemini 3 Pro with audio transcription and a new pelican benchmark”
These days I'm already finding it 100x easier/informative to have complicated charged discussions (eg immigration) with Gemini than with actual people.
Recommends · Feb 2026 · in “The consequences of task switching in supervisory programming”
I found Gemini 2.5 Pro to be AMAZING during preview and then it's performance and quality unceremoniously dropped month after month once it went live.
Mixed · Dec 2025 · in “OpenAI declares 'code red' as Google catches up in AI race”
Gemini 3.0 being able to laugh about their own creator, plus actually having a self-deprecating sense of humor, is the more impressive feat here.
Recommends · Dec 2025 · in “Show HN: Gemini Pro 3 imagines the HN front page 10 years from now”
I've definitely noticed Gemini's tendency to return the image basically unchanged, but not noticed it being worse or better for images of people.
Mixed · Nov 2025 · in “We ran over 600 image generations to compare AI image models”
Counts from 1,795,640 Hacker News comments, Nov 2025 to Nov 2026. How we count · Report a mistake