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

Gemini 2.5 Pro Preview

developers.googleblog.com

Post reply on HN
Print view View original

131–140 of 728 posts

Re: Gemini 2.5 Pro Preview

#131

Post by sroussey »

diggan wrote: post #118
sitkack wrote: post #85

Earlier quoted context omitted.

LLMs are extremely poor at following negative instructions, tell them what to do, not what not to do.

Ok, so saying "Implement feature X" leads to a ton of comments. How do you rewrite that comment to not include "don't write comments" while making the output not containing comments? "Write only source code, no plain text with special characters in the beginning of the line" or what are you suggesting here in practical terms?

“Constrain all comments to a single block at the top of the file. Be concise.”

Or something similar that does not rely on negation.

Re: Gemini 2.5 Pro Preview

#132

Post by jjani »

ramesh31 wrote: post #21
shostack wrote: post #7

Earlier quoted context omitted.

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…

The designs itself are still done by humans, I presume?

Re: Gemini 2.5 Pro Preview

#133

Post by hmate9 »

nashashmi wrote: post #113

I keep hearing good things about Gemini online and offline. I wrote them off as terrible when they first launched and have not looked back since. How are they now? Sufficiently good? Competent? Competitive? Or limited? My needs are very consumer oriented, not programming/api stuff.

Probably the best one right now, their deep research is also very good.

Re: Gemini 2.5 Pro Preview

#135

Post by pzo »

segphault wrote: post #18

My frustration with using these models for programming in the past has largely been around their tendency to hallucinate APIs that simply don't exist. The Gemini 2.5 models, both pro and flash, seem significantly less susceptible to this than any other model I've tried. There are still significant limitations, no amount of prompting will get current models to approach abstraction and architecture the way a person doe…

I feel your pain. Cursor has docs features but many times when I pointed to check @docs and selected one recently indexed one it sometimes still didn't get it. I still have to try contex7 mcp which looks promising:

https://github.com/upstash/context7

Re: Gemini 2.5 Pro Preview

#136

Post by nolist_policy »

mgw wrote: post #72
puika wrote: post #57

Earlier quoted context omitted.

I have the same issue plus unnecessary refactorings (that break functionality). it doesn't matter if I write a whole paragraph in the chat or the prompt explaining I don't want it to change anything else apart from what is required to fulfill my very specific request. It will just go rogue and massacre the entirety of the file.

This has also been my biggest gripe with Gemini 2.5 Pro. While it is fantastic at one-shotting major new features, when wanting to make smaller iterative changes, it always does big refactors at the same time. I haven't found a way to change that behavior through changes in my prompts. Claude 3.7 Sonnet is much more restrained and does smaller changes.

Can't you just commit the relevant parts? The git index is made for this sort of thing.

Re: Gemini 2.5 Pro Preview

#137

Post by kubb »

energy123 wrote: post #81
uh_uh wrote: post #44

Earlier quoted context omitted.

Noticed this too. There's something funny about billion dollar models being handicapped by stuck buttons.

The Gemini app has a number of severe bugs that impacts everyone who uses it, and those bugs have persisted for over 6 months. There's something seriously dysfunctional and incompetent about the team that built that web app. What a way to waste the best LLM in the world.

It's the company. Letting incompetent people who are vocal rise to the top is a part of Google's culture, and the internal performance review process discourages excellence - doing the thousand small improvements that makes a product truly great is invisible to it, so nobody does it.

Software that people truly love is impossible to build in there.

Re: Gemini 2.5 Pro Preview

#138

Post by sitkack »

sroussey wrote: post #131
diggan wrote: post #118

Earlier quoted context omitted.

Ok, so saying "Implement feature X" leads to a ton of comments. How do you rewrite that comment to not include "don't write comments" while making the output not containing comments? "Write only source code, no plain text with special characters in the beginning of the line" or what are you suggesting here in practical terms?

“Constrain all comments to a single block at the top of the file. Be concise.” Or something similar that does not rely on negation.

I also include something about "Target the comments towards a staff engineer that favors concise comments that focus on the why, and only for code that might cause confusion."

I also try and get it to channel that energy into the doc strings, so it isn't buried in the source.

Re: Gemini 2.5 Pro Preview

#139

Post by jerkstate »

NeutralForest wrote: post #125
koakuma-chan wrote: post #55

Earlier quoted context omitted.

No, it's just bad. I've been writing a lot of Python code past two days with Gemini 2.5 Pro Preview, and all of its code was like: ```python def whatever(): --- SECTION ONE OF THE CODE --- ... --- SECTION TWO OF THE CODE --- try: [some "dangerous" code] except Exception as e: logging.error(f"Failed to save files to {output_path}: {e}") # Decide whether to raise the error or just warn # raise IOError(f"Failed to save…

I'm seeing it trying to catch blind exceptions in Python all the time. I see it in my colleagues code all the time, it's driving me nuts.

There are a bunch of stupid behaviors of LLM coding that will be fixed by more awareness pretty soon. Imagine putting the docs and code for all of your libraries into the context window so it can understand what exceptions might be thrown!

Re: Gemini 2.5 Pro Preview

#140

Post by mrinterweb »

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.

If you don't want so many comments, have you tried asking the AI for fewer comments. Seems like something a little prompt engineering could solve.
Post reply on HN