Through my Kagi subscription I get access to quite a few models [1] but I tend to rely on Qwen3 (fast) for quick questions and Qwen3 (reasoning) when I want a more structured approach, for example, when I am researching a topic.
I have tried the same approach with Kimi K2.5 and GLM 5 but I keep going back fo Qwen3.
I also have access to Perplexity which is quite decent to be honest, but I prefer to keep everything in Kagi.
> [...] it's much easier to fine-tune a "general" model into performing some very specific custom task (like classifying text, or translation, etc)
Is this fine-tunning process similar to training models? As in, do you need exhaustive resources? Or can this be done (realistically) on a consumer-grade GPU?
> But are we really at the point yet where people are running local models without knowing what they are running them on..?
I can only speak for myself: it can be daunting for a beginner to figure out which model fits your GPU, as the model size in GB doesn't directly translate to your GPU's VRAM capacity.
There is value in learning what fits and runs on your system, but that's a different discussion.
Pi ships with powerful defaults but skips features like sub-agents and plan mode
Does anyone have an idea as to why this would be a feature? don't you want to have a discussion with your agent to iron out the details before moving onto the implementation (build) phase?
In any case, looks cool :)
EDIT 1: Formatting
EDIT 2: Thanks everyone for your input. I was not aware of the extensibility model that pi had in mind or that you can also iterate your plan on a PLAN.md file. Very interesting approach. I'll have a look and give it a go.
Agreed. I rarely find the guardrails of plan to be necessary; I basically never use it on opencode. I have some custom commands I use to ask for plan making, discussion.
As for subagents, Pi has sessions. And it has a full session tree & forking. This is one of my favorite things, in all harnesses: build the thing with half the context, then keep using that as a checkpoint, doing new work, from that same branch point. It means still having a very usable lengthy context window but having good fundamental project knowledge loaded.
If anything, this makes them more legit than Anthropic because they are paying for the content, whereas Anthropic just stole *all* the data they got a hold of. So, in this case the Chinese AI labs stand on higher moral ground LOL.
The article touches a bit on how Sega basically lost.
There is literally a whole documentary about this: Console Wars, where they go deep into how Sega lost the battle: https://en.wikipedia.org/wiki/Console_Wars_(film)
Have you investigated more on this topic? like, anything similar in concept that competes with Serena? if so, have you tested it/them? what are your thoughts?
@pmarreck, Serena developer here. We invite you to contribute to Serena in order to make it better. Serena is free & open-source, and it already robustly addresses the key issues preventing coding agents from being truly efficient even in complex software development projects (while being highly configurable).
We don't believe CLI is the way to go though, because advanced code intelligence simply cannot be spawned on the fly and thus benefits from a stateful process (such as a language server or an IDE instance).
I have tried the same approach with Kimi K2.5 and GLM 5 but I keep going back fo Qwen3.
I also have access to Perplexity which is quite decent to be honest, but I prefer to keep everything in Kagi.
1: https://help.kagi.com/kagi/ai/assistant.html#available-llms
reply