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

281–290 of 728 posts

Re: Gemini 2.5 Pro Preview

#281

Post by satvikpendem »

siscia wrote: post #217
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…

This problem have been solved by LSP (language server protocol), all we need is a small server behind MCP that can communicate LSP information back to the LLM and get the LLM to use by adding to the prompt something like: "check your API usage with the LSP" The unfortunate state of open source funding makes buildings such simple tool a loosing adventure unfortunately.

This already happens in agent modes in IDEs like Cursor or VSCode with Copilot, it can check for errors with the LSP.

Re: Gemini 2.5 Pro Preview

#282

Post by fwip »

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.

Really? I haven't tried Gemini 2.5 yet, but my main complaint with Claude 3.7 is this exact behavior - creating 200+ line diffs when I asked it to fix one function.

Re: Gemini 2.5 Pro Preview

#283

Post by gilbetron »

kweingar wrote: post #64
mattlondon wrote: post #46

Earlier quoted context omitted.

It's already much improved on the early days. But I wonder when we'll be happy? Do we expect colleagues friends and family to be 100% laser-accurate 100% of the time? I'd wager we don't. Should we expect that from an artificial intelligence too?

I expect my calculator to be 100% accurate 100% of the time. I have slightly more tolerance for other software having defects, but not much more.

It's your option not to use it. However, this is a competitive environment and so we will see who pulls out ahead, those that use AI as a productivity multiplier versus those that do not. Maybe that multiplier is less than 1, time will tell.

Re: Gemini 2.5 Pro Preview

#284

Post by SparkyMcUnicorn »

mliker wrote: post #54

The "video to learning app" feature is a cool concept (see it in AI Studio). I just passed in two separate Stanford lectures to see if it could come up with an interesting interactive app. The apps it generated weren't too useful, but I can see with more focus and development, it'd be a game changer for education.

Anyone know of any coding agents that support video inputs?

Web chat interfaces are great, but copy/paste gets old fast.

Re: Gemini 2.5 Pro Preview

#285

Post by thr0waway39290 »

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…

Replacing stackoverflow is definitely helpful, but the best use case for me is how much it helps in high-level architecture and planning before starting a project.

Re: Gemini 2.5 Pro Preview

#286

Post by izacus »

pb7 wrote: post #184
asadotzler wrote: post #130

Earlier quoted context omitted.

And a $2.99 drugstore slim wallet calculator with solar power gets it right 100% of the time while billion dollar LLMs can still get arithmetic wrong on occasion.

My hammer can't do any arithmetic at all, why does anyone even use them?

What you're being asked is to stop trying to hammer every single thing that comes into your vicinity. Smashing your computer with a hammer won't create code.

Re: Gemini 2.5 Pro Preview

#287

Post by izacus »

scarab92 wrote: post #180
kortilla wrote: post #119

Earlier quoted context omitted.

If colleagues lie with the certainty that LLMs do, they would get fired for incompetence.

I wish that were true, but I’ve found that certain types of employees do confidently lie as much as llms, especially when answering “do you understand” type questions

And we try to PIP and fire those as well, not turn everyone else into them.

Re: Gemini 2.5 Pro Preview

#288

Post by arresin »

qwertox wrote: post #277

I have my issues with the code Gemini Pro in AI Studio generates without customized "System Instructions". It turns a well readable code-snippet of 5 lines into a 30 line snippet full of comments and mostly unnecessary error handling. Code which becomes harder to reason about. But for sysadmin tasks, like dealing with ZFS and LVM, it is absolutely incredible.

I’ve found the same thing. I don’t use it for code any more because it produces highly verbose and inefficient code that may work but is ugly and subtly brittle.

Re: Gemini 2.5 Pro Preview

#289

Post by arresin »

ionwake wrote: post #30

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?

The one with exp in the name is free (you may have to add it yourself) but they train on you. And after a certain limit it becomes paid).

Re: Gemini 2.5 Pro Preview

#290

Post by darepublic »

Jordan-117 wrote: post #247
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 recently needed to recommend some IAM permissions for an assistant on a hobby project; not complete access but just enough to do what was required. Was rusty with the console and didn't have direct access to it at the time, but figured it was a solid use case for LLMs since AWS is so ubiquitous and well-documented. I actually queried 4o, 3.7 Sonnet, and Gemini 2.5 for recommendations, stripped the list of duplicate…

Listen I don't blame any mortal being for not grokking the AWS and Google docs. They are a twisting labyrinth of pointers to pointers some of them deprecated though recommended by Google itself.
Post reply on HN