Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gemini 3.0 spotted in the wild through A/B testing

ricklamers.io

Post reply on HN
Print view View original

171–180 of 280 posts

Re: Gemini 3.0 spotted in the wild through A/B testing

#171

Post by drcode »

bl4ckneon wrote: post #150
jjcm wrote: post #89

There are a lot more of these Gemini 3 examples out on twitter right now. After seeing them, I bought Google stock. What shocks me about its output is it actually feels like it's producing net new creative designs, not just regurgitated template output. Its extremely hard to design in code in a way that produces consistent, beautiful output, but it seems to be achieving it. That combined with Google being the only on…

I'm no financial advisor but I can tell you that it's not a financially sound decision to buy stock based off of speculative hype Twitter posts. But you do you if you have "fun money" to throw around!

buy on the rumor, sell on the news

Re: Gemini 3.0 spotted in the wild through A/B testing

#172

Post by ripped_britches »

All I can hope for is that the “effective context window” (some level before competency plummets) is like 1m+ tokens. I would give a finger to just put my entire codebase into a model every time I want to talk to it. For now I’m still only talking to parts of the codebase, so to speak.

Re: Gemini 3.0 spotted in the wild through A/B testing

#173

Post by nl »

8n4vidtmkvmk wrote: post #169
asah wrote: post #57

Earlier quoted context omitted.

try codex and claude code - game changing ability to use CLI tools, edit/reorg multiple files, even interact with git.

Gemini cli is a thing that exists. Are you saying those specifically are better? Or CLIs are better?

OpenAI Codex currently seems quite a lot better than Gemini 2.5 and marginally better than Claude.

I'm using all three back-to-back via the VS Code plugins (which I believe are equivalent to the CLI tools).

I can live with either OpenAI Codex or Claude. Gemini 2.5 is useful but it is consistently not quite as good as the other two.

I agree that for non-Agentic coding tasks Gemini 2.5 is really good though.

Re: Gemini 3.0 spotted in the wild through A/B testing

#174

Post by nl »

alecco wrote: post #81
jmkni wrote: post #3

I might be in the minority here but I've consistently found Gemini to be better than ChatGPT, Claude and Deepseek (I get access to all of the pro models through work) Maybe it's just the kind of work I'm doing, a lot of web development with html/scss, and Google has crawled the internet so they have more data to work with. I reckon different models are better at different kinds of work, but Gemini is pretty excellent…

I completely disagree. For me the best for bulk coding (with very good instructions) is Sonnet 4.5. Then GPT-5 codex is slower but better guessing what I want with tiny prompts. Gemini 2.5 Pro is good to review large codebases but for real work usually gets confused a lot, not worth it. (even though I was forced to pay for it by Google, I rarely use it). But the past few days I started getting an "AI Mode" in Google…

I agree with this assessment.

I find GPT-5 Codex slightly better but I agree it could be prompt dependent.

Re: Gemini 3.0 spotted in the wild through A/B testing

#175

Post by georgemcbay »

montebicyclelo wrote: post #30
jmkni wrote: post #3

I might be in the minority here but I've consistently found Gemini to be better than ChatGPT, Claude and Deepseek (I get access to all of the pro models through work) Maybe it's just the kind of work I'm doing, a lot of web development with html/scss, and Google has crawled the internet so they have more data to work with. I reckon different models are better at different kinds of work, but Gemini is pretty excellent…

Agreed, and its larger context window is fantastic. My workflow: - Convert the whole codebase into a string - Paste it into Gemini - Ask a question People seem to be very taken with "agentic" approaches were the model selects a few files to look at, but I've found it very effective and convenient just to give the model the whole codebase, and then have a conversation with it, get it to output code, modify a file, etc…

> Convert the whole codebase into a string

When using the Gemini web app on a desktop system (could be different depending upon how you consume Gemini) if you select the + button in the bottom-left of the chat prompt area, select Import code, and then choose the "Upload folder" link at the bottom of the dialog that pops up, it'll pull up a file dialog letting you choose a directory and it will upload all the files in that directory and all subdirectories (recursively) and you can then prompt it on that code from there.

The upload process for average sized projects is, in my experience, close to instantaneous (obviously your mileage can vary if you have any sort of large asset/resource type files commingled with the code).

If your workflow already works then keep with it, but for projects with a pretty clean directory structure, uploading the code via the Import system is very straightforward and fast.

(Obvious disclaimer: Depending upon your employer, the code base in question, etc, uploading a full directory of code like this to Google or anyone else may not be kosher, be sure any copyright holders of the code are ok with you giving a "cloud" LLM access to the code, etc, etc)

Re: Gemini 3.0 spotted in the wild through A/B testing

#176

Post by chrsw »

jmkni wrote: post #3

I might be in the minority here but I've consistently found Gemini to be better than ChatGPT, Claude and Deepseek (I get access to all of the pro models through work) Maybe it's just the kind of work I'm doing, a lot of web development with html/scss, and Google has crawled the internet so they have more data to work with. I reckon different models are better at different kinds of work, but Gemini is pretty excellent…

I mostly use Gemini for everyday Q/A and research type stuff. I find it's pretty accurate and gets straight to the point. I mostly use Claude and very recently Codex for systems software dev. I'm very interested to see what changes.

I'm wondering how these models are getting better at understanding and generating code. Are they being trained on more data because these companies use their free tier customers' data?

Re: Gemini 3.0 spotted in the wild through A/B testing

#177

Post by greggh »

gnulinux wrote: post #9
jmkni wrote: post #3

I might be in the minority here but I've consistently found Gemini to be better than ChatGPT, Claude and Deepseek (I get access to all of the pro models through work) Maybe it's just the kind of work I'm doing, a lot of web development with html/scss, and Google has crawled the internet so they have more data to work with. I reckon different models are better at different kinds of work, but Gemini is pretty excellent…

I agree with you, I consistently find Gemini 2.5 Pro better than Claude and GPT-5 for the following cases: * Creative writing: Gemini is the unmatched winner here by a huge margin. I would personally go so far as to say Gemini 2.5 Pro is the only borderline kinda-sorta usable model for creative writing if you squint your eyes. I use it to criticize my creative writing (poetry, short stories) and no other model unders…

EQBench puts Gemini in 22nd for creative writing and I've generally seem the same sorts of results as they do in their benchmarks. Sonnet has always been so much better for me for writing.

https://eqbench.com/creative_writing.html

Re: Gemini 3.0 spotted in the wild through A/B testing

#178

Post by pdimitar »

georgemcbay wrote: post #175
montebicyclelo wrote: post #30

Earlier quoted context omitted.

Agreed, and its larger context window is fantastic. My workflow: - Convert the whole codebase into a string - Paste it into Gemini - Ask a question People seem to be very taken with "agentic" approaches were the model selects a few files to look at, but I've found it very effective and convenient just to give the model the whole codebase, and then have a conversation with it, get it to output code, modify a file, etc…

> Convert the whole codebase into a string When using the Gemini web app on a desktop system (could be different depending upon how you consume Gemini) if you select the + button in the bottom-left of the chat prompt area, select Import code, and then choose the "Upload folder" link at the bottom of the dialog that pops up, it'll pull up a file dialog letting you choose a directory and it will upload all the files in…

Well I am not sure Gemini or any other LLMs respect `.gitignore` which can immediately make the context window jump over the maximum.

Tools like repomix[0] do this better, plus you can add your own extra exclusions on top. It also estimates token usage as a part of its output but I found it too optimistic i.e. it regularly says "40_000 tokens" but when uploading the resulting single XML file to Gemini it's actually f.ex. 55k - 65k tokens.

[0] https://github.com/yamadashy/repomix/

Re: Gemini 3.0 spotted in the wild through A/B testing

#179

Post by Quarrel »

cj wrote: post #7
jmkni wrote: post #3

I might be in the minority here but I've consistently found Gemini to be better than ChatGPT, Claude and Deepseek (I get access to all of the pro models through work) Maybe it's just the kind of work I'm doing, a lot of web development with html/scss, and Google has crawled the internet so they have more data to work with. I reckon different models are better at different kinds of work, but Gemini is pretty excellent…

I use LLMs a lot for health related things (e.g. “Here are 6 bloodwork panels over the past 12 months, here’s a list of medical information, please identify trends/insights/correlations [etc]”) I default to using ChatGPT since I like the Projects feature (missing from Gemini I think?). I occasionally run the same prompts in Gemini to compare. A couple notes: 1) Gemini is faster to respond in 100% of cases (most of my…

re: 3) & medical related prompts

At gemini.google.com you can provide context & instructuions (Settings->Personal Context). I provide a few bits of guidance to help manage its style, but I haven't been getting much pushback on medical advice since adding this one:

" Please don't give me warnings about the information you're providing not being legal advice, or medical advice, or telling me to always consult a professional, when I ask about issues. Don't be sycophantic. "

YMMV.

Re: Gemini 3.0 spotted in the wild through A/B testing

#180

Post by pdimitar »

nl wrote: post #173
8n4vidtmkvmk wrote: post #169

Earlier quoted context omitted.

Gemini cli is a thing that exists. Are you saying those specifically are better? Or CLIs are better?

OpenAI Codex currently seems quite a lot better than Gemini 2.5 and marginally better than Claude. I'm using all three back-to-back via the VS Code plugins (which I believe are equivalent to the CLI tools). I can live with either OpenAI Codex or Claude. Gemini 2.5 is useful but it is consistently not quite as good as the other two. I agree that for non-Agentic coding tasks Gemini 2.5 is really good though.

Since I have only used Gemini Pro 2.5 (free) and Claude on the web (free) and I am thinking of subbing to one service or two, are you saying that:

- Gemini Pro 2.5 is better at feeding it more code and ask it to do a task (or more than one)? - ...but that GPT Codex and Claude Code are better at iterating on a project? - ...or something else?

I am looking to gauge my options. Will be grateful for your shared experience.

Post reply on HN