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

Ask HN: What default model do you use and why?

news.ycombinator.com

Post reply on HN
Print view View original

61–70 of 104 posts

Re: Ask HN: What default model do you use and why?

#61

Post by the__alchemist »

montroser wrote: post #48

It pains me to read these answers so far. Listen, for 99%+ of your web and mobile tasks, deepseek-v4.1-flash is all you need. It is blazing fast, super cheap, and quite proficient. It acts responsibly, has top-notch vision for evaluating its own UI work, and is far less smug and flowery than any of the Anthropic models. For what it's worth, here's a take on its speed vs cost vs intelligence: https://artificialanalysi…

What pains you in particular? Any specific posts, trends, or tool choices here?

Re: Ask HN: What default model do you use and why?

#62

Post by montroser »

the__alchemist wrote: post #61
montroser wrote: post #48

It pains me to read these answers so far. Listen, for 99%+ of your web and mobile tasks, deepseek-v4.1-flash is all you need. It is blazing fast, super cheap, and quite proficient. It acts responsibly, has top-notch vision for evaluating its own UI work, and is far less smug and flowery than any of the Anthropic models. For what it's worth, here's a take on its speed vs cost vs intelligence: https://artificialanalysi…

What pains you in particular? Any specific posts, trends, or tool choices here?

It pains me to see so, so many dollars going to Anthropic. There is either massive inefficiency in there, or else its users are getting fleeced.

In cost-per-task, it's a 32x multiple Fable vs DS41. Either it really does cost them more electricity/gpu, or else they are succeeding convincing the masses that Anthropic's models are necessary for everyday tasks, when this is truly just not the case. Either way seems a tragedy.

Especially regrettable from my perspective, is the idea that to do computer programming in these modern times, you have to fork over an amount comparable to many people's monthly rent. Even if your employer is happy to direct their funds that way, we lose quite something when recreational coding comes with a substantial personal monetary cost.

https://artificialanalysis.ai/#price-and-cost

Re: Ask HN: What default model do you use and why?

#63

Post by cassianoleal »

montroser wrote: post #62
the__alchemist wrote: post #61

Earlier quoted context omitted.

What pains you in particular? Any specific posts, trends, or tool choices here?

It pains me to see so, so many dollars going to Anthropic. There is either massive inefficiency in there, or else its users are getting fleeced. In cost-per-task, it's a 32x multiple Fable vs DS41. Either it really does cost them more electricity/gpu, or else they are succeeding convincing the masses that Anthropic's models are necessary for everyday tasks, when this is truly just not the case. Either way seems a tra…

Another happy DS41 user here. When I talk to friends with Claude subscriptions, they're not doing anything more complicated or better than I am, but are paying through their noses.

Re: Ask HN: What default model do you use and why?

#64

Post by the__alchemist »

montroser wrote: post #62
the__alchemist wrote: post #61

Earlier quoted context omitted.

What pains you in particular? Any specific posts, trends, or tool choices here?

It pains me to see so, so many dollars going to Anthropic. There is either massive inefficiency in there, or else its users are getting fleeced. In cost-per-task, it's a 32x multiple Fable vs DS41. Either it really does cost them more electricity/gpu, or else they are succeeding convincing the masses that Anthropic's models are necessary for everyday tasks, when this is truly just not the case. Either way seems a tra…

I wish my monthly rent were $20!

Re: Ask HN: What default model do you use and why?

#65

Post by AaronAPU »

montroser wrote: post #48

It pains me to read these answers so far. Listen, for 99%+ of your web and mobile tasks, deepseek-v4.1-flash is all you need. It is blazing fast, super cheap, and quite proficient. It acts responsibly, has top-notch vision for evaluating its own UI work, and is far less smug and flowery than any of the Anthropic models. For what it's worth, here's a take on its speed vs cost vs intelligence: https://artificialanalysi…

I pay $200 month and literally have never a single time run out of usage, for Codex + Pro chat. It is better than DeepSeek and at least it supports a US company. Your pain isn’t important to me.

Re: Ask HN: What default model do you use and why?

#66

Post by jakevoytko »

My workhorse is Opus orchestrating Sonnet or Sol orchestrating Luna, depending on which ecosystem I'm using this week. I'm a backend engineer, so for tasks that either interact with the machine learning or client codebases, I have Fable (Medium) review across the product spec, tech spec, and all the codebases after the implementation is done (haven't tried this workflow with Astra yet, don't know if it's a good reviewer).

As a side project, I'm doing an experimental task now (having Astra implement my own personal Google Docs clone, OT and everything, for my blog), and it feels more capable than Fable but needs to be watched closer than Fable. It is obsessed with verification and evidence to the point that I've needed to make some absolute rules to stop it from repeatedly e.g. making unit tests with 10,000 test cases with 5+ hours of runtime

For well-defined coding tasks, I'd default to either Luna or Sonnet, or hell, just writing it by hand.

Re: Ask HN: What default model do you use and why?

#67

Post by prettyblocks »

cassianoleal wrote: post #63
montroser wrote: post #62

Earlier quoted context omitted.

It pains me to see so, so many dollars going to Anthropic. There is either massive inefficiency in there, or else its users are getting fleeced. In cost-per-task, it's a 32x multiple Fable vs DS41. Either it really does cost them more electricity/gpu, or else they are succeeding convincing the masses that Anthropic's models are necessary for everyday tasks, when this is truly just not the case. Either way seems a tra…

Another happy DS41 user here. When I talk to friends with Claude subscriptions, they're not doing anything more complicated or better than I am, but are paying through their noses.

Do you use a 3rd party provider or use deepseek directly?

Re: Ask HN: What default model do you use and why?

#68

Post by gtadesktop1 »

I used Claude too, but I was banned so I searched for new like you yet and found Google AI Studio. It has a Playground-Mode for the newest models you usually have to pay but in the Playground-Mode you don't pay one cent. You can use Gemini 3.8 Flash and you can give him system instructions. For example you can say "You're a AI Agent that helps me with my mobile app" and he helps you with your mobile app. It has a context window up to 1 million tokens and it's fully free. If the limit is reached you can only click on the "+" icon on the top right and say him what you did attach all project files and tell him what you need. He reads the files you attached and helps you like the old chat.

Re: Ask HN: What default model do you use and why?

#69

Post by oidar »

hgoel wrote: post #37

For personal needs I use a local Qwen3.8-Next-Flash setup on a GB10 cluster. For work, Github Copilot with either GPT 5 mini or toss up between Opus/Sol depending on the complexity of the task. Used to pay for a Claude 20x plan and did everything in Opus, but I hate how it talks now and recent events (OAI scooping, Anthropic's spying, third party Chinese model hosts stealing and selling credentials) have really pushe…

> on a GB10 cluster

I'd love to hear more about your setup. I have a single GB10 and am thinking about adding an additional one.

Re: Ask HN: What default model do you use and why?

#70

Post by nvme0n1p1 »

gtadesktop1 wrote: post #68

I used Claude too, but I was banned so I searched for new like you yet and found Google AI Studio. It has a Playground-Mode for the newest models you usually have to pay but in the Playground-Mode you don't pay one cent. You can use Gemini 3.8 Flash and you can give him system instructions. For example you can say "You're a AI Agent that helps me with my mobile app" and he helps you with your mobile app. It has a con…

The way you're calling a computer program "he" and "him" really skeeves me out for some reason.
Post reply on HN