Gemini 2.5 Pro Preview • Hacker News Board

Re: Gemini 2.5 Pro Preview

#21

Post by ramesh31 » Tue, May 06, 2025, 3:35 PM UTC

shostack wrote: post #7

ramesh31 wrote: post #4

>Best-in-class frontend web development It really is wild to have seen this happen over the last year. The days of traditional "design-to-code" FE work are completely over. I haven't written a line of HTML/CSS in months. If you are still doing this stuff by hand, you need to adapt fast. In conjunction with an agentic coding IDE and a few MCP tools, weeks worth of UI work are now done in hours to a higher level of qua…

What does your tool and model stack look like for this?

Cline with Gemini 2.5 (https://cline.bot/)

Framelink MCP (https://github.com/GLips/Figma-Context-MCP)

Playwright MCP (https://github.com/microsoft/playwright-mcp)

Pull down designs via Framelink, optionally enrich with PNG exports of nodes added as image uploads to the prompt, write out the components, test/verify via Playwright MCP.

Gemini has a 1M context size now, so this applies to large mature codebases as well as greenfield. The key thing here is the coding agent being really clever about maintaining its' context; you don't need to fit an entire codebase into a single prompt in the same way that you don't need to fit the entire codebase into your head to make a change, you just need enough context on the structure and form to maintain the correct patterns.

Re: Gemini 2.5 Pro Preview

#22

Post by herpdyderp » Tue, May 06, 2025, 3:36 PM UTC

I agree it's very good but the UI is still usually an unusable, scroll-jacking disaster. I've found it's best to let a chat sit for around a few minutes after it has finished printing the AI's output. Finding the `ms-code-block` element in dev tools and logging `$0.textContext` is reliable too.

Re: Gemini 2.5 Pro Preview

#23

Post by Scene_Cast2 » Tue, May 06, 2025, 3:36 PM UTC

ranyume wrote: post #11

I don't know if I'm doing something wrong, but every time I ask gemini 2.5 for code it outputs SO MANY comments. An exaggerated amount of comments. Sections comments, step comments, block comments, inline comments, all the gang.

It also does super defensive coding. Not that it's a bad thing in general, but I write a lot of prototype code.

Re: Gemini 2.5 Pro Preview

#24

Post by ChadMoran » Tue, May 06, 2025, 3:37 PM UTC

GaggiX wrote: post #15

ranyume wrote: post #11

I don't know if I'm doing something wrong, but every time I ask gemini 2.5 for code it outputs SO MANY comments. An exaggerated amount of comments. Sections comments, step comments, block comments, inline comments, all the gang.

You can ask to not use comments or use less comments, you can put this in the system prompt too.

I've tried this, aggressively and it still does it for me. I gave up.

Re: Gemini 2.5 Pro Preview

#25

Post by Benjammer » Tue, May 06, 2025, 3:38 PM UTC

ranyume wrote: post #11

I don't know if I'm doing something wrong, but every time I ask gemini 2.5 for code it outputs SO MANY comments. An exaggerated amount of comments. Sections comments, step comments, block comments, inline comments, all the gang.

I've found that heavily commented code can be better for the LLM to read later, so it pulls in explanatory comments into context at the same time as reading code, similar to pulling in @docs, so maybe it's doing that on purpose?

Re: Gemini 2.5 Pro Preview

#26

Post by OsrsNeedsf2P » Tue, May 06, 2025, 3:38 PM UTC

herpdyderp wrote: post #22

I agree it's very good but the UI is still usually an unusable, scroll-jacking disaster. I've found it's best to let a chat sit for around a few minutes after it has finished printing the AI's output. Finding the `ms-code-block` element in dev tools and logging `$0.textContext` is reliable too.

Loading the UI on mobile while on low bandwidth is also a non-starter. It simply doesn't work.

Re: Gemini 2.5 Pro Preview

#27

Post by crat3r » Tue, May 06, 2025, 3:38 PM UTC

So, are people using these tools without the org they work for knowing? The amount of hoops I would have to jump through to get either of the smaller companies I have worked for since the AI boom to let me use a tool like this would make it absolutely not worth the effort.

I'm assuming large companies are mandating it, but ultimately the work that these LLMs seem poised for would benefit smaller companies most and I don't think they can really afford using them? Are people here paying for a personal subscription and then linking it to their work machines?

Re: Gemini 2.5 Pro Preview

#28

Post by guestbest » Tue, May 06, 2025, 3:38 PM UTC

ranyume wrote: post #11

I don't know if I'm doing something wrong, but every time I ask gemini 2.5 for code it outputs SO MANY comments. An exaggerated amount of comments. Sections comments, step comments, block comments, inline comments, all the gang.

What kind of problems are you putting in where that is the solution? Just curious.

Re: Gemini 2.5 Pro Preview

#29

Post by dlojudice » Tue, May 06, 2025, 3:39 PM UTC

ramesh31 wrote: post #4

>Best-in-class frontend web development It really is wild to have seen this happen over the last year. The days of traditional "design-to-code" FE work are completely over. I haven't written a line of HTML/CSS in months. If you are still doing this stuff by hand, you need to adapt fast. In conjunction with an agentic coding IDE and a few MCP tools, weeks worth of UI work are now done in hours to a higher level of qua…

> are now done in hours to a higher level of quality

However, I feel that there is a big difference between the models. In my tests, using Cursor, Clause 3.7 Sonnet has a much more refined "aesthetic sense" than other models. Many times I ask "make it more beautiful" and it manages to improve, where other models just can't understand it.

Re: Gemini 2.5 Pro Preview

#30

Post by ionwake » Tue, May 06, 2025, 3:40 PM UTC

Is it possible to sue this with Cursor? If so what is the name of the model? gemini-2.5-pro-preview ?

edit> Its gemini-2.5-pro-preview-05-06

edit>Cursor syas it doesnt have "good support" et, but im not sure if this is a defualt message when it doesnt recognise a model? is this a big deal? should I wait until its officially supported by cursor?

Just trying to save time here for everyone - anyone know the answer?