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

Gemini 2.5 Flash

developers.googleblog.com

Post reply on HN
Print view View original

491–500 of 582 posts

Re: Gemini 2.5 Flash

#491

Post by dmos62 »

kccqzy wrote: post #59
xbmcuser wrote: post #50

For a non programmer like me google is becoming shockingly good. It is giving working code the first time. I was playing around with it asked it to write code to scrape some data of a website to analyse. I was expecting it to write something that would scrape the data and later I would upload the data to it to analyse. But it actually wrote code that scraped and analysed the data. It was basic categorizing and counti…

That's the opposite experience of my wife who's in tech but also a non programmer. She wanted to ask Gemini to write code to do some basic data analysis things in a more automated way than Excel. More than once, Gemini wrote a long bash script where some sed invocations are just plain wrong. More than once I've had to debug Gemini-written bash scripts. As a programmer I knew how bash scripts aren't great for readabil…

Which Gemini was it? I've been using 2.5 Flash all day for programming ClojureScript via roo code and it's been great. Provided I'm using agent orchestration, a memory bank, and having it write docs for code it will work on.

Re: Gemini 2.5 Flash

#492

Post by darksaints »

ramesh31 wrote: post #485
MetaWhirledPeas wrote: post #484

Earlier quoted context omitted.

> 100% of my casual AI usage is now in Gemini and I look forward to asking it questions on deep topics because it consistently provides me with insight. It's probably great for lots of things but it doesn't seem very good for recent news. I asked it about recent accusations around xAI and methane gas turbines and it had no clue what I was talking about. I asked the same question to Grok and it gave me all sorts of de…

>It's probably great for lots of things but it doesn't seem very good for recent news. You are missing the point here. The LLM is just the “reasoning engine” for agents now. Its corpus of facts are meaningless, and shouldn’t really be relied upon for anything. But in conjunction with a tool calling agentic process, with access to the web, what you described is now trivially doable. Single shot LLM usage is not really…

That’s all fine and dandy, but if you google anything related to llm agents, you get 1000 answers to 100 questions, companies hawking their new “visual programming” agent composers, and a ton of videos of douchebags trying to be the Steve Jobs of AI. The concept I’m sure is fine, but execution of agentic anything is still the Wild Wild West and nobody knows what they’re really doing.

Re: Gemini 2.5 Flash

#493

Post by fuzzylightbulb »

_blk wrote: post #461
zoogeny wrote: post #131

Google making Gemini 2.5 Pro (Experimental) free was a big deal. I haven't tried the more expensive OpenAI models so I can't even compare, only to the free models I have used of theirs in the past. Gemini 2.5 Pro is so much of a step up (IME) that I've become sold on Google's models in general. It not only is smarter than me on most of the subjects I engage with it, it also isn't completely obsequious. The model push…

Have you tried Grok 3? It's a bit verbose for my taste even when prompted to be brief but answers seem better/more researched and less opinionated. It's also more willing to answer questions where the other models block an answer.

A lot of people don't want to patronize the businesses of an unabashed Nazi sympathizer. There are more important things in life than model output quality.

Re: Gemini 2.5 Flash

#494

Post by greentea23 »

deanmoriarty wrote: post #178

Genuine naive question: when it comes to Google HN has generally a negative view of it (pick any random story on Chrome, ads, search, web, working at faang, etc. and this should be obvious from the comments), yet when it comes to AI there is a somewhat notable “cheering effect” for Google to win the AI race that goes beyond a conventional appreciation of a healthy competitive landscape, which may appear as a bit of a…

I prefer OpenAI and Anthropic big time because they are fresh players with less dominance over other aspects of digital life. Not having to login to an insidious tracker like Google is worth significantly worse performance. Although I have little FOMO here avoiding Gemini because evaluating these models on real world use cases remains quite subjective imo.

Re: Gemini 2.5 Flash

#495

Post by latemedium »

There's an important difference between Gemini and Claude that I'm not sure how to quantify. I often use shell-connected LLMs (LLMs with a shell tool enabled) to take care of basic CSV munging / file-sorting tasks for me - I work in data science so there's a lot of this. When I ask Claude to do something, it carefully looks at all the directories and files before doing anything. Gemini, on the other hand, blindly jumps in and just starts moving stuff around. Claude executes more tools and is a little slower, but it almost always gets the right answer because it appropriately gathers the right context before really trying to solve the problem. Gemini doesn't seem to do this at all, but it makes a world of difference for my set of problems. Curious to see if others have had the same experience or if its just a quirk of my particular set of tasks

Re: Gemini 2.5 Flash

#496

Post by energy123 »

latemedium wrote: post #495

There's an important difference between Gemini and Claude that I'm not sure how to quantify. I often use shell-connected LLMs (LLMs with a shell tool enabled) to take care of basic CSV munging / file-sorting tasks for me - I work in data science so there's a lot of this. When I ask Claude to do something, it carefully looks at all the directories and files before doing anything. Gemini, on the other hand, blindly jum…

What's a shell connected LLM and how to do that?

Re: Gemini 2.5 Flash

#497

Post by kmacdough »

energy123 wrote: post #496
latemedium wrote: post #495

There's an important difference between Gemini and Claude that I'm not sure how to quantify. I often use shell-connected LLMs (LLMs with a shell tool enabled) to take care of basic CSV munging / file-sorting tasks for me - I work in data science so there's a lot of this. When I ask Claude to do something, it carefully looks at all the directories and files before doing anything. Gemini, on the other hand, blindly jum…

What's a shell connected LLM and how to do that?

Look up Claude Code, Cursor, Aider and VSCode's agent integration. Generally, tools to use AI more actively for development. There are others as well. Plenty of info around. Here's not the place for a tutorial.

Re: Gemini 2.5 Flash

#498

Post by rjurney »

I am building a knowledge graph using BAML [baml-py] to extract documents [it's opinionated towards docs] and then PySpark to ETL the data into a node / edge list. GPT4o got few relations... Gemini 2.5 got so many it was nuts, all accurate but not all from the article! I had to reign it in and instruct it not to build so vast a graph. Really cool, it knows a LOT about semiconductors :)

Re: Gemini 2.5 Flash

#499

Post by profsummergig »

I tried this prompt in both Gemini 2.5 Pro, and in ChatGPT.

"Draw me a timeline of all the dynasties of China. Imagine a horizontal line. Start from the leftmost point and draw segments for the start and end of each dynasty. For periods where multiple dynasties existed simultaneously draw parallel lines or boxes to represent the concurrent rule."

Gemini's response: "I'm just a language model, so I can't help you with that."

ChatGPT's response: an actual visual timeline.

Re: Gemini 2.5 Flash

#500

Post by vunderba »

behnamoh wrote: post #154
minimaxir wrote: post #139

One hidden note from Gemini 2.5 Flash when diving deep into the documentation: for image inputs, not only can the model be instructed to generated 2D bounding boxes of relevant subjects, but it can also create segmentation masks! https://ai.google.dev/gemini-api/docs/image-understanding#se... At this price point with the Flash model, creating segmentation masks is pretty nifty. The segmentation masks are a bit of a g…

Wait, did they just kill YOLO, at least for time-insensitive tasks?

Well no. You can run/host YOLO which means not having to submit potentially sensitive information to a company that generates a large amount of revenue from targeted advertising.
Post reply on HN