Gemini

53 engineers on Hacker News describe using Gemini first-hand: 19 endorse it, 8 regret it, 11 are mixed.

64%trust
53first-hand users
25in production
endorse 19mixed 11regret 8uses, no opinion

“I use gemini in prod via google cloud... for my niche they are the best for good quality at great speeds.”

mixed · production · 2 yr · hypendev · 2026-10-29 · source ↗ · wrong label?

“Gemini is the only model that I still see regularly flat-out hallucinate, e.g. the other day it told me we were using a particular technology (Fivetran) on a project”

regret · production · sandcat_ · 2026-08-16 · source ↗ · wrong label?

“We run an agent company ... Gemini is great for computer use.”

endorse · production · pimeys · 2026-07-30 · source ↗ · wrong label?

“on the cost:quality:latency:adherence picture, flash wins hands down for structured extraction.”

endorse · production · urbsgpw · 2026-07-21 · source ↗ · wrong label?

“We have products in prod that use Gemini because they're better than any other model at the specific task.”

endorse · production · deaux · 2026-07-21 · source ↗ · wrong label?

“We found gemini 3 flash to be the best model as of now, when it comes to bang for the buck”

endorse · production · okwasniewski · 2026-06-18 · source ↗ · wrong label?

“I keep getting notification from my tooling that gemini models are overloaded so we switched you to openai.”

regret · production · dzhiurgis · 2026-04-24 · source ↗ · wrong label?

“we started seeing ~90% error rates getting 429s over the weekend. (So we switched to GPT 5.4 nano.)”

regret · production · jbellis · 2026-04-22 · source ↗ · wrong label?

“I worked on a startup experimenting with gemini-2.0-flash... We found it to be extremely successful at needle-in-a-haystack type problems.”

endorse · production · elliotto · 2026-01-15 · source ↗ · wrong label?

“I tried to use two AI models (ChatGPT 5.2 and the latest Gemini) to serve as ersatz Referees... it was an exercise in pointless, frustrating disaster. Never again.”

regret · personal · qubex · 2026-01-09 · source ↗ · wrong label?

“I found Gemini to be pretty great at validating an exported KiCAD netlist against the relevant datasheets with a few caveats.”

mixed · personal · maz- · 2026-01-05 · source ↗ · wrong label?

“Gemini 3 Preview is already doing better at some tasks (but frequently goes insane, sadly).”

mixed · personal · atombender · 2025-12-31 · source ↗ · wrong label?

“They are pretty good at writing code after I thoroughly described what to do, step by step. If you miss a small detail they get loose”

mixed · personal · 1 yr · zsoltkacsandi · 2025-12-30 · source ↗ · wrong label?

“I’ve been using Google's Gemini for image generation, but the watermarks are often a hurdle for clean designs.”

mixed · personal · h2bomb · 2025-12-28 · source ↗ · wrong label?

“I have pushed Gemini 2.5 Pro further than I thought possible when it comes to ridiculously over complicated (by necessity) structured output.”

endorse · personal · teruakohatu · 2025-12-26 · source ↗ · wrong label?

“I've been using Gemini / Antigravity to make a virtual pet for my kids using Love2D / lua.”

endorse · personal · boca_honey · 2025-12-23 · source ↗ · wrong label?

“Gemini also sucks at search for some reason”

regret · personal · andai · 2025-12-23 · source ↗ · wrong label?

“I've been using gemini-3-flash the last few days and it is quite good”

endorse · personal · verdverm · 2025-12-21 · source ↗ · wrong label?

“Ive been using 2.5 pro or flash a ton at work and the pro was not noticeably more accurate, but significantly slower, so I used flash way more.”

endorse · production · gorbot · 2025-12-18 · source ↗ · wrong label?

“It's a prompt I've been using for years. Gemini has been the best of the bunch”

endorse · personal · eterm · 2025-12-17 · source ↗ · wrong label?

“I've been using 2.5 flash and it is pretty bad. 1 out of 5 answers it gives will be a lie.”

regret · personal · freedomben · 2025-12-17 · source ↗ · wrong label?

“I've been using the preview flash model exclusively since it came out, the speed and quality of response is all I need at the moment.”

endorse · personal · bearjaws · 2025-12-17 · source ↗ · wrong label?

“I have already many use cases in prod where Gemini Flash 2.0 did a great job, and that's an old model by today's standards”

endorse · production · epolanski · 2025-12-15 · source ↗ · wrong label?

“Gemini handles every single one of my uses cases much better and consistently gives better answers. Only downsides are in the polish department”

mixed · personal · tenpoundhammer · 2025-12-11 · source ↗ · wrong label?

“Nice, it works. Let's try using live video. Open the docs, you get it mentioned a bunch of times but 0 documentation on how to actually do it.”

mixed · personal · thecupisblue · 2025-12-11 · source ↗ · wrong label?

“Only Google Gemini barely cut the mustard.”

mixed · personal · egberts1 · 2025-10-11 · source ↗ · wrong label?

“having much fun currently with gemini”

endorse · personal · wglb · 2025-09-05 · source ↗ · wrong label?

“have you ever try to get anything done well with Gemini? ... But Gemini? never again.”

regret · personal · fpia · 2025-07-21 · source ↗ · wrong label?

“I used gemini to create a CAD file transposition tool that utilized a simple GUI tailor made for the files my company works with.”

endorse · production · Workaccount2 · 2025-06-25 · source ↗ · wrong label?

“The performance of top-tier models is still unmatched.”

endorse · production · PaulShin · 2025-06-09 · source ↗ · wrong label?

“I can ask Gemini 2.5 (1M context length) crazy things ... and get really good high quality answers.”

endorse · production · phyalow · 2025-04-29 · source ↗ · wrong label?

“Gemini developer experience was stupidly easy. Easy to add a file "part" to a prompt.”

endorse · production · lazypenguin · 2025-02-05 · source ↗ · wrong label?

“sometimes the results are amazing, but you have to proofread it all because they occasionally go off the rails... Still overall a time saver.”

mixed · personal · richard_todd · 2024-12-18 · source ↗ · wrong label?

“We have been using Gemini 1.5 Flash at enterprise scale... and we have yet to see hallucinations”

endorse · production · ajcp · 2024-12-17 · source ↗ · wrong label?

“The models do just fine on "work" but are terrible for "thinking".”

mixed · personal · ComputerGuru · 2024-12-11 · source ↗ · wrong label?

“I've been using Gemini Flash for free through the API using Cline for VS Code.”

mixed · personal · gman83 · 2024-12-11 · source ↗ · wrong label?

“We use Gemini flash in prod. The latency and cost is just unbeatable”

endorse · production · tempusalaria · 2024-10-18 · source ↗ · wrong label?

“I have tried using GPT4 & gemini extensively, and the amount of bullshit generated makes it unreliable if you don't already know the domain.”

regret · personal · huimang · 2024-03-12 · source ↗ · wrong label?

“the default free chats with Gemini 3.5 Flash for general searching”

neutral · personal · einhard · 2026-11-05 · source ↗ · wrong label?

“at the moment Gemini Pro and Flash latest runs the show for you”

neutral · production · raxwan · 2026-10-24 · source ↗ · wrong label?

“I ported over my busiest app stage from openrouter/gemini to haiku”

neutral · production · schmookeeg · 2026-10-20 · source ↗ · wrong label?

“I've been using Gemini 3.8 Flash for a long time”

neutral · personal · fantasticwaddle · 2026-10-19 · source ↗ · wrong label?

“I had been using Gemini to build OpenScad models.”

neutral · personal · zdp7 · 2026-10-16 · source ↗ · wrong label?

“made a bunch of workloads we had on Luna or Gemini 10x cheaper and 2x faster (previously used non reasoning version for latency reasons)”

neutral · production · zurfer · 2026-09-19 · source ↗ · wrong label?

“I had a production image processing using Gemini 2.5 Flash Lite (which is getting discontinued in October)”

neutral · production · testycool · 2026-09-18 · source ↗ · wrong label?

“We run Gemini fast for random end user queries for general staff.”

neutral · production · FuriouslyAdrift · 2026-09-04 · source ↗ · wrong label?

“Where we used Gemini before Deepseek v4 Flash is taking the lead on price.”

neutral · production · pimeys · 2026-08-14 · source ↗ · wrong label?

“With Opus4.5, Gemini 3 and gpt 5.2, it's now 20%, maybe 50% if we only talk about personal code output.”

neutral · production · orwin · 2025-12-28 · source ↗ · wrong label?

“I've mainly been using claude code and a bit of Gemini/Amp/Droid”

neutral · personal · sixhobbits · 2025-12-27 · source ↗ · wrong label?

“I've been using composer-1 in Cursor for a few weeks and also switching back and forth between it, Gemini Flash 3, Claude Opus 4.5, Claude Sonnet 4.5 and GPT 5.2.”

neutral · production · santoriv · 2025-12-19 · source ↗ · wrong label?

“Claude, Gemini and Codex are currently working together on implementing FIPA ACL inter agent communication”

neutral · personal · vmitro · 2025-12-16 · source ↗ · wrong label?

“I use Gemini 3 but only in specific high value use cases.”

neutral · personal · mark_l_watson · 2025-12-03 · source ↗ · wrong label?

“He ended up learning how to use Gemini to accelerate his learning”

neutral · personal · veesahni · 2024-12-03 · source ↗ · wrong label?