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

Developers are choosing older AI models

augmentcode.com

Post reply on HN
Print view View original

91–100 of 179 posts

Re: Developers are choosing older AI models

#91

Post by RamtinJ95 »

kristianp wrote: post #89
KronisLV wrote: post #3

For development use cases, I switched to Sonnet 4.5 and haven't looked back. I mean, sure, sometimes I also use GPT-5 (and mini) and Gemini 2.5 Pro (and Flash), and also Cerebras Code just switched to providing GLM 4.6 instead of the previous Qwen3 Coder so those as well, but in general the frontier models are pretty good for development and I wouldn't have much reason to use something like Sonnet 4 or 3.7 or whateve…

What tool are you using to enable switching between so many models?

Something like opencode probably, that’s what I have been using to freely and very easily switch between models and keep all my same workflows. It’s phenomenal really

Re: Developers are choosing older AI models

#93

Post by omgmajk »

ruszki wrote: post #63
s1mplicissimus wrote: post #23

Earlier quoted context omitted.

Most people I know can't afford to leak business insider information to 3rd party SaaS providers, so it's unfortunately not really an option.

But… they do all the time. Almost everybody uses some mix of Office, Slack, Notion, random email providers, random “security” solutions etc. The exception is the opposite. The only thing prevents info leaking is ToS, and there are options for that even with LLMs. Nothing changed regarding that.

All of those things are hosted on-prem in the bigger orgs I have worked in.

Re: Developers are choosing older AI models

#94

Post by radicalbyte »

jen729w wrote: post #27
rhdunn wrote: post #24

Earlier quoted context omitted.

A 4090 has 24GB of VRAM allowing you to run a 22B model entirely in memory at FP8 and 24B models at Q6_K (~19GB). A 5090 has 32GB of VRAM allowing you to run a 32B model in memory at Q6_K. You can run larger models by splitting the GPU layers that are run in VRAM vs stored in RAM. That is slower, but still viable. This means that you can run the Qwen3-Coder-30B-A3B model locally on a 4090 or 5090. That model is a Mix…

Honestly though how many people reading this do you think have that setup vs. 85% of us being on a MBx? > The Qwen3-Coder-480B-A35B model could also be run on a 4090 or 5090 by splitting the active 35B parameters across VRAM and RAM. Reminds me of running Doom when I had to hack config.sys to forage 640KB of memory. Less than 0.1% of the people reading this are doing that. Me, I gave $20 to some cloud service and I c…

> Reminds me of running Doom when I had to hack config.sys to forage 640KB of memory.

The good old days of having to do crazy nutty things to get Elite II: Frontier, Magic Carpet, Worms, Xcom: UFO Enemy Unknown, Syndicate et cetera to actually run on my PC :-)

Re: Developers are choosing older AI models

#95

Post by yass0 »

LouisSayers wrote: post #56

I wish we could pin down not only the model but also the way the UI works as well. Last week Claude seemed to have a shift in the way it works. The way it summarises and outputs its results is different. For me it's gotten worse. Slower, worse results, more confusing narrowing down what actually changed etc etc. Long story short, I wish I was able to checkpoint the entire system and just revert to how it was previous…

You can install or using a specific version of claude by pinning it.

Like `npx @anthropic-ai/claude-code@2.0.14` or `npm install -g @anthropic-ai/claude-code@2.0.14`

Re: Developers are choosing older AI models

#96

Post by thw_9a83c »

KronisLV wrote: post #3

For development use cases, I switched to Sonnet 4.5 and haven't looked back. I mean, sure, sometimes I also use GPT-5 (and mini) and Gemini 2.5 Pro (and Flash), and also Cerebras Code just switched to providing GLM 4.6 instead of the previous Qwen3 Coder so those as well, but in general the frontier models are pretty good for development and I wouldn't have much reason to use something like Sonnet 4 or 3.7 or whateve…

For development use cases, it's best to use multiple models anyway. E.g. my favorite model is the Gemini 2.5 Pro, but there are certain cases where Qwen3 Coder gives much better results. (Gemini likes to overthink.) It's like having a team of competent developers provide their opinions. For important parts (security, efficiency, APIs), it's always good to get opinions from different sources.

Re: Developers are choosing older AI models

#97

Post by popcornricecake »

nxpnsv wrote: post #88
popcornricecake wrote: post #83

Earlier quoted context omitted.

Doesn't spare you from having to interact with the popup. This is probably the single dumbest law to ever have been made. It wastes everyone's time, and not insignificantly. While the browser is and always was in full control of cookies, nobody checks whether the popup actually even does what it says. And since it's a waste of your time in the first place, who takes the time to report illegal ones, much less has any…

Single dumbest law ever made? I think that’s underestimating the stupidity of many laws.

Possibly. I just can't think of other stupid ones that have a comparably wide impact.

Re: Developers are choosing older AI models

#98

Post by lukan »

CuriouslyC wrote: post #44
JanSt wrote: post #28

Earlier quoted context omitted.

I have canceled my Claude Max subscription because Sonnet 4.5 is just too unreliable. For the rest of the month I'm using Opus 4.1 which is much better but seems to have much lower usage limits than before Sonnet 4.5 was released. When I hit 4.1 Opus limits I'm using Codex. I will probably go through with the Codex pro subscription.

Definitely do it. You get a lot of deep research, access to GPT5 Pro, Sora and the Codex limits are MUCH higher.

Curious why this is downvoted? Wrong information?

Re: Developers are choosing older AI models

#99

Post by simonw »

omgmajk wrote: post #93
ruszki wrote: post #63

Earlier quoted context omitted.

But… they do all the time. Almost everybody uses some mix of Office, Slack, Notion, random email providers, random “security” solutions etc. The exception is the opposite. The only thing prevents info leaking is ToS, and there are options for that even with LLMs. Nothing changed regarding that.

All of those things are hosted on-prem in the bigger orgs I have worked in.

I don't think Slack or Notion have on-prem/self-hosted options.

Re: Developers are choosing older AI models

#100

Post by simonw »

mcny wrote: post #84
Dilettante_ wrote: post #77

Earlier quoted context omitted.

But the progress goes both ways: In five years, you would still want to use whatever is running on the cloud supercenters. Just like today you could run gpt-2 locally as a coding agent, but we want the 100x-as-powerful shiny thing.

That would be great if that was the case but my understanding is that the progress is plateauing. I don't know how much of this is anthorpic / Google / openAI holding itself back to save money and how much is the state of the art improvement slowing down though. I can imagine there could be a 64 GB GPU in five years as absurd as it feels to type that today.

What gives you the impression the progress is plateauing?

I'm finding the difference just between Sonnet 4 and Sonnet 4.5 to be meaningful in terms of the complexity of tasks I'm willing to use them for.

Post reply on HN