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

31–40 of 104 posts

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

#31

Post by martythemaniak »

vallerie wrote: post #6

I've found good success with the new Gemini models on Antigravity. Granted I use my models either: - like a fancy auto complete (here are some stub methods, they should do X, fill them in) - using fairly detailed plans and test harnesses, so blowing up the world is hard The 3.X Flash family have been fairly capable models, and the selling point for me is just raw speed. Gemini is noticeably faster than the competitio…

Same. I have a promo plan that's currently $3/month, which gets you a model that's almost opus, very fast speeds, and very generous limits.

There's no Gemini pro model currently, so you gotta pair that with a 20 openai plan for access to more advanced stuff if you need it.

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

#32

Post by pighive »

codazoda wrote: post #21

I use Sonnit for my personal work and Opus for my professional work. For my personal stuff, I'm on a small $20 plan, so I need to use tokens conservatively. I was very rarely exceeding limits until I built a Dark Software Factory. It's not as efficient at token use. So, I use Sonnit over Opus here. At work I have a $100 plan that I rarely exceed so I use Opus. I have access to Fable too, and I did use it a lot while…

How is the Dark Software Factory set up? What is it producing?

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

#33

Post by donatj »

I feel like the odd man out ITT but Terra has been absolutely amazing for me and totally blows Sonnet out of the water. My company pays for Claude so I use Sonnet in the office but at home I use Terra and I find it far more likely to one shot some very decent code.

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

#34

Post by notnmeyer »

mariocesar wrote: post #25
sourcecodeplz wrote: post #18

Earlier quoted context omitted.

i can not believe you really use Haiku?

To ask for web search, simple commands and research, or passing logs to analyze it's more than enough Here is the script https://github.com/mariocesar/dotfiles/blob/main/common/.loc...

this is a really neat idea. thanks for sharing!

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

#36

Post by rsyring »

Context will be important for answers to be meaningfully comparable:

- LLM expense budget

- What type of dev: work, personal, real time spaceship thrust vectoring, html contact forms for family, etc.

- human in the loop with short as possible turns, software factories that can run for days, or something in the middle

Just off the top of my head. I'm sure there are others I'm missing.

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

#37

Post by hgoel »

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 pushed me towards local AI for personal needs. Am not allowed to use Chinese models for work even if self-hosted so not much choice there.

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

#40

Post by tiluha »

amelius wrote: post #26

Reading through this thread, I notice not many people are using models from the Chinese AI labs ...

My current vibe/playing around setup is deepseek v4.1 flash with opus/sol as advisor agent, dsv4.1flash agents for self review and final review with opus/sol. I love how fast and cheap deepseek is. Using omp as harness.

Privacy policy is not great with deepseek api, but you are always just trusting their word with any hosted llm and in theory i could at least self host the models i use from deepseek.

Post reply on HN