Live data from Hacker News

Developers are choosing older AI models

augmentcode.com

131–140 of 179 posts

Re: Developers are choosing older AI models

#131

Isn’t this obvious? When you have a task you think is hard. You give it to a cleverer model. When a task is straight forward you give it to an older one.

Why are you hell bent on using a LLM model to solve your problem?

If I have a straight forward task, I give it to an LLM.

If I have a task I think is hard, I plan how I will tackle it, and then handle it myself in a series of steps.

LLM usage has become an end in itself in your development process.

Re: Developers are choosing older AI models

#132
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?

You can also switch between models with aider https://aider.chat/

Re: Developers are choosing older AI models

#134
post #28
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…

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.

> [...] 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 [...]

Yes, it's down from 40h/week to 3-5h/week on Max plan, effectively. A real bummer. See my comment here [1] regarding [2].

[1] https://news.ycombinator.com/item?id=45604301

[2] https://github.com/anthropics/claude-code/issues/8449

Re: Developers are choosing older AI models

#135

Some missing context (pun intended) is that Augment code has recently switched to a per-token instead of per-message pricing model. This hasn't gone down particularly well, but that's another story. But it may well be that users drop back to older models in the expectation it will use less tokens. Personally, I stopped using GPT-5 as it would just be tool call after tool call without ever stopping to tell you what th…

I have to get better at interrupting Sonnet 4.5 when it starts going down a rabbit hole I didn't ask it to, it's too bad the incentives are mixed up and Anthropic gets more money the longer the bot spirals.

Re: Developers are choosing older AI models

#136
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?

Octofy (https://octofy.ai), it also allows answering with multiple models for one prompt.

Re: Developers are choosing older AI models

#137
post #28
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…

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.

Opus 4.1 is better, but imo not 5 to 6 times the price better.

Re: Developers are choosing older AI models

#138
post #90

Earlier quoted context omitted.

In my personal experience, it's very common for big companies to host email, messengers, conferencing software on their own servers.

Yes, then they use Outlook for example. Have you checked the ToS of the new Outlook version for commoners? They flat out state that they can use all of your emails for whatever they want. Also, companies host for example an Exchange server on prem; and guess, what it connects to? Why you can usually access account at outlook.com?

Your on premise exchange server has zero connections to outlook.com. OWA (Outlook Web Access) looks similar to outlook.com but has otherwise nothing to do with it.

Re: Developers are choosing older AI models

#140
I am building my agent and hoard old LLM's like they are a precious commodity. Older models are less censored, more flavorful and don't have that RL slop factor. Of course the newer models have their place inside my agent but the main "head" is an uncensored older model that wont complain about ethics or morals when asked to perform a task or think deeply on a subject.
Post reply on HN