Earlier quoted context omitted.
$100 Claude max is the best subscription I’ve ever had. Well worth every penny now
Or a $40 GitHub copilot plan also gets you a lot of Opus usage.
Missing a lot without claude code tho
Gemini 3 Flash: Frontier intelligence built for speed
601–609 of 609 posts
Re: Gemini 3 Flash: Frontier intelligence built for speed
#602Earlier quoted context omitted.
It sounds like you already know what sales peoples incentives are. They don't care about the tiny players who wanna use tiny slices. I was referring to people who are trying to push PB through these. GCPs policies make a lot of sense if they are trying to get major players to switch their compute/data host to reduce overall costs.
The cost ratio is the same.
It isn't. You don't pay "msrp" at scale :)
Re: Gemini 3 Flash: Frontier intelligence built for speed
#603I'll take the hit to my 401k for this to all just go away. The comments here sound ridiculous.
Can you give an example of some ridiculous comments
Re: Gemini 3 Flash: Frontier intelligence built for speed
#604Earlier quoted context omitted.
May I ask your internal benchmark ? I'm building a new set of benchmarks and testing suite for agentic workflows using deepwalker [0]. How do you design your benchmark suite ? would be really cool if you can give more details. [0] https://deepwalker.xyz
Shared a bit more here - https://news.ycombinator.com/item?id=46314047 . But pretty rudimentary, nothing special. Also did not know about deepwalker, looks quite interesting - you building it?
I personally know the team who builds the product.
Re: Gemini 3 Flash: Frontier intelligence built for speed
#605Earlier quoted context omitted.
Curious to learn what a “product benchmark” looks like. Is it evals you use to test prompts/models? A third party tool? Examples from the wild are a great learning tool, anything you’re able to share is appreciated.
Everyone should have their own "pelican riding a bicycle" benchmark they test new models on. And it shouldn't be shared publicly so that the models won't learn about it accidentally :)
I am asking the models to generate an image where fictional characters play chess or Texas Holdem. None of them can make a realistic chess position or poker game. Always something is off like too many pawns or too may cards, or some cards being ace-up when they shouldn't be.
Re: Gemini 3 Flash: Frontier intelligence built for speed
#606Earlier quoted context omitted.
Considering that they will make a lot of money with enterprise, yes, that's exactly what I think. What I don't think is that I can take seriously someone's opinion on enterprise service's privacy after they write "LMAO" in capslock in their post.
I just know many people here complained about the very unclear way, google for example communicates what they use for training data and what plan to choose to opt out of everything, or if you (as a normal buisness) even can opt out. Given the whole volatile nature of this thing, I can imagine an easy "oops, we messed up" from google if it turns out they were in fact using allmost everything for training. Second thing…
To be fair, we all know googles terms are ambiguous as hell. It would not be a big surprise nor an outright lie if they did use it.
Its different if they proclaimed outright they won't use it and then do.
Not that any of this is right, it wouldn't be a true betrayal.
On a related note, these terms to me are a great example of success for EU GDPR regulations, and regulations on corporates in general. It's clear as day, additional protections are afforded to EU residents in these terms purely due to the law.
Re: Gemini 3 Flash: Frontier intelligence built for speed
#607Earlier quoted context omitted.
The cost ratio is the same.
It isn't. You don't pay "msrp" at scale :)
You're off by orders of magnitude. A million tokens is about 5 MB of text and costs $0.20 to process in something like Gemini 3 Flash.
Hence, a terabyte of text would cost about $42,000 to run through a pareto-frontier "cheap" model.
The most expensive cloud egress fee I could quickly find is $185 per terabyte (Azure South America Internet egress).
Hence, AI processing is 200x as expensive as bandwidth, or put another way, even a long-distance international egress at "exorbitant cloud retail pricing" is a mere 0.5% of the cost.
Petabytes, exabytes, etc... just adds digits to both the token cost and bandwidth cost in sync and won't significantly shift the ratio. If anything, bandwidth costs will go down and AI costs go up because: output tokens, smarter models, retries, multiple questions for the same data, etc...
Re: Gemini 3 Flash: Frontier intelligence built for speed
#608Earlier quoted context omitted.
Or a $40 GitHub copilot plan also gets you a lot of Opus usage.
Missing a lot without claude code tho
I've tried both, and I'm still not sure. Claude Code steers more towards a hands-off, vibe coding approach, which I often regret later. With Copilot I'm more involved, which feels less 'magical' and takes me more time, but generally does not end in misery.
Re: Gemini 3 Flash: Frontier intelligence built for speed
#609Earlier quoted context omitted.
just switch to Opencode and stop locking yourself into a particular providers way of doing things. There's a plugin for everything that mimics anything the others are doing
Being open does not magically make everything better. People are willing to pay for Claude Code for many valid reasons. You are also assuming I have never used OpenCode, which is incorrect. Claude is simply my preference. I see all of these tools as IDEs. Whether someone locks into VS Code, JetBrains, Neovim, or Sublime Text comes down to personal preference. Everyone works differently, and that is completely fine.
I use claude on opencode.
I'm not sure you even understand what opencode is.