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

There is minimal downside to switching to open models

marble.onl

Post reply on HN
Print view View original

21–30 of 351 posts

Re: There is minimal downside to switching to open models

#21

Post by nemomarx »

TacticalCoder wrote: post #9
julianlam wrote: post #6

I think it's interesting that people write off open weight models because they're "a few months behind" proprietary models. I know LLMs move at the speed of light (especially these past few quarters), but if Opus and GPT "a few months ago" were really like open weight models, then there's really no reason to not switch, especially for those who were using these models a few months ago. Your codebase didn't change, so…

> I think it's interesting that people write off open weight models because they're "a few months behind" proprietary models. The really interesting thing is that it's typically those very same accounts who were explaining, a few months ago, that thanks to their commercial model they were gaining so much time and producing so much fantastic code. A few months passes and suddenly the open-source model have caught up w…

My most charitable interpretation that there's some honeymoon effect for each release, and people genuinely feel very productive and useful for 2-3 months. By the time the next big model release happens they've seen some issues or run into something that makes them feel like the new model will fix all that and improve their flow so much, etc.

Not unusual in the tech space, but this has been basically constantly happening for two years now? I can't imagine the improvements are more than incremental at this point.

Re: There is minimal downside to switching to open models

#22

Post by Gigachad »

0gs wrote: post #3
DANmode wrote: post #2

But, what model are you using? and what hardware are you using?

yeah, on a 96GB Mac Studio and Gemma+Qwen, it's definitely fully doable. fully doable but not really for coding on 16GB. but svelter models and cheaper (eventually) hardware are coming!

I suspect hosted and local will converge when hardware prices come down and API prices go up. The massive rate of datacenter build out will be unsustainable. Right now the hosted models are massively cheaper than buying the hardware and running it yourself which signals that hosted is very subsidized.

Re: There is minimal downside to switching to open models

#23

Post by tonfreed »

julianlam wrote: post #6

I think it's interesting that people write off open weight models because they're "a few months behind" proprietary models. I know LLMs move at the speed of light (especially these past few quarters), but if Opus and GPT "a few months ago" were really like open weight models, then there's really no reason to not switch, especially for those who were using these models a few months ago. Your codebase didn't change, so…

Even just one of the smaller models is good enough for the grunt work I use them for 90% of the time. Currently doing most of my home hobby projects with OpenCode Go and Qwen 3.7 Plus, it's not great at diagnosing issues in the code, but if I can clearly articulate a test suite or boilerplate refactoring it works fine.

Re: There is minimal downside to switching to open models

#24

Post by fluidcruft »

0gs wrote: post #3
DANmode wrote: post #2

But, what model are you using? and what hardware are you using?

yeah, on a 96GB Mac Studio and Gemma+Qwen, it's definitely fully doable. fully doable but not really for coding on 16GB. but svelter models and cheaper (eventually) hardware are coming!

If you don't have that hardware thr math of buying a depreciating computer is challenging if you are satisfied with the $100/month plans ($1200/year). A 96GB Mac Studio is ~$4k. I think if you have the hardware already as a sunk cost then yes it makes sense. But I'm not sure it is worth spending $4k for today's hardware vs waiting for newer hardware in a few years.

Re: There is minimal downside to switching to open models

#25

Post by causality0 »

I know open models have gotten quite good in many tasks such as coding or composition, but are there any that can access the internet and retrieve data like ChatGPT, Claude, etc can?

I do have to admit I have recently begun wishing I could pay five dollars a month for a "just answer the fucking question" plan that would give me results without the guardrails and without the constant simpering and ego-stroking. I keep finding myself going a quick evaluation of "is it faster for me to skim search results myself or to construct an elaborate narrative to make an AI give me a real answer".

Re: There is minimal downside to switching to open models

#26

Post by linzhangrun »

causality0 wrote: post #25

I know open models have gotten quite good in many tasks such as coding or composition, but are there any that can access the internet and retrieve data like ChatGPT, Claude, etc can? I do have to admit I have recently begun wishing I could pay five dollars a month for a "just answer the fucking question" plan that would give me results without the guardrails and without the constant simpering and ego-stroking. I keep…

You can let the AI solve it itself, and then it will provide two solutions: implement a local search service (easily blocked), or purchase a Web Search API service

Re: There is minimal downside to switching to open models

#29

Post by CJefferson »

pkulak wrote: post #28

Sure. But OpenAI is the same price. Why would I pay $18/month for z.ai when OpenAI is $20/month?

One big advantage I’ve found — people get attached to models (including me). With open models if you find one that works perfectly for you but the next version doesn’t, you can run the old one forever (or someone will for you)

Re: There is minimal downside to switching to open models

#30

Post by jbverschoor »

kgeist wrote: post #11
julianlam wrote: post #6

I think it's interesting that people write off open weight models because they're "a few months behind" proprietary models. I know LLMs move at the speed of light (especially these past few quarters), but if Opus and GPT "a few months ago" were really like open weight models, then there's really no reason to not switch, especially for those who were using these models a few months ago. Your codebase didn't change, so…

Every new proprietary model is "groundbreaking" and "look, it just solved task X that no other model could solve," only to be referred to as "that crappy previous-generation model" a month later. So yeah, I'm totally fine using Kimi-2.7, GLM-5.2 or Deepseek-v4. I think we've already hit the ceiling and most improvements now seem to be from harness improvements and slightly better RL to improve reasoning/tool calling.

Not only that, but to me it seems that after a week the intelligence is being downscaled or routed. Maybe because of lack of capacity
Post reply on HN