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

291–300 of 728 posts

Re: Gemini 2.5 Pro Preview

#291

Post by kweingar »

gilbetron wrote: post #283
kweingar wrote: post #64

Earlier quoted context omitted.

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.

Agreed. The nice thing is that I am told by HN and Twitter that agentic workflows makes code tasks very easy, so if it turns out that using these tools multiplies productivity, then I can just start using them and it will be easy. Then I am caught up with the early adopters and don't need to worry about being out-competed by them.

Re: Gemini 2.5 Pro Preview

#292

Post by yousif_123123 »

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…

The opposite problem is also true. I was using it to edit code I had that was calling the new openai image API, which is slightly different from the dalle API. But Gemini was consistently "fixing" the OpenAI call even when I explained clearly not to do that since I'm using a new API design etc. Claude wasn't having that issue.

The models are very impressive. But issues like these still make me feel they are still more pattern matching (although there's also some magic, don't get me wrong) but not fully reasoning over everything correctly like you'd expect of a typical human reasoner.

Re: Gemini 2.5 Pro Preview

#293

Post by cdolan »

danenania wrote: post #228
lukeschlather wrote: post #108

Earlier quoted context omitted.

I take preview to mean the model may be retired on an accelerated timescale and replaced with a "real" model so it's dangerous to put into prod unless you are paying attention.

Scheduled tasks in ChatGPT are useful for keeping track of these kinds of things. You can have it check daily whether there's a change in status, price, etc. for a particular model (or set of models).

I appriciate that you are trying to help

But I do not want to have to build a network of bots with non-deterministic outputs to simply stay on top of versions

Re: Gemini 2.5 Pro Preview

#295

Post by danenania »

cdolan wrote: post #293
danenania wrote: post #228

Earlier quoted context omitted.

Scheduled tasks in ChatGPT are useful for keeping track of these kinds of things. You can have it check daily whether there's a change in status, price, etc. for a particular model (or set of models).

I appriciate that you are trying to help But I do not want to have to build a network of bots with non-deterministic outputs to simply stay on top of versions

Neither do I, but it's the best solution I've found so far. It beats checking models/prices manually every day to see if anything has changed, and it works well enough in practice.

But yeah, some kind of deterministic way to get alerts would be better.

Re: Gemini 2.5 Pro Preview

#296

Post by tangjurine »

jjani wrote: post #183
sauwan wrote: post #151

Earlier quoted context omitted.

I'd be surprised if this was a new base model. It sounds like they just did some post-training RL tuning to make this version specifically stronger for coding, at the expense of other priorities.

Every frontier model now is a distill of a larger unpublished model. This could be a slightly smaller distill, with potentially the extra tuning you're mentioning.

Any info on this?

Re: Gemini 2.5 Pro Preview

#298

Post by bezier-curve »

redox99 wrote: post #92
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…

Making LLMs know what they don't know is a hard problem. Many attempts at making them refuse to answer what they don't know caused them to refuse to answer things they did in fact know.

The best way around this is to dump documentation of the APIs you need them privy to into their context window.

Re: Gemini 2.5 Pro Preview

#299

Post by ajross »

mynameisvlad wrote: post #269
ajross wrote: post #252

Earlier quoted context omitted.

This is a circular semantic argument. You're saying knowledge is knowledge because it's correct, where guessing is guessing because it's a guess. But "is it correct?" is precisely the question you're asking the poor LLM to answer in the first place. It's not helpful to just demand a computation device work the way you want, you need to actually make it work. Also, too, there are whole subfields of philosophy that mak…

I mean, it clearly does based on your comments showing a need for a correctness check to disambiguate between made up "hallucinations" and actual "knowledge" (together, a "consistently correct guess"). The fact that you are humanizing an LLM is honestly just plain weird. It does not have feelings. It doesn't care that it has to answer "is it correct?" and saying poor LLM is just trying to tug on heartstrings to make…

FWIW "asking the poor to do " is an extremely common idiom. It's used as a metaphor for an inappropriate or unachievable design requirement. Nothing to do with LLMs. I work on microcontrollers for a living.

Re: Gemini 2.5 Pro Preview

#300

Post by toomuchtodo »

yousif_123123 wrote: post #292
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…

The opposite problem is also true. I was using it to edit code I had that was calling the new openai image API, which is slightly different from the dalle API. But Gemini was consistently "fixing" the OpenAI call even when I explained clearly not to do that since I'm using a new API design etc. Claude wasn't having that issue. The models are very impressive. But issues like these still make me feel they are still mor…

It seems like the fix is straightforward (check the output against a machine readable spec before providing it to the user), but perhaps I am a rube. This is no different than me clicking through a search result to the underlying page to verify the veracity of the search result surfaced.
Post reply on HN