← Back to context

Comment by hosteur

12 days ago

I haven't tried a whole lot. I tried Cline which I found hugely unstable and slow. I also tried the Google and Anthropic CLI ones very early on. They were a bit unstable at the time. So I guess I just stopped looking around much after trying Kilo Code because it gets the job done.

I am curious, when do you typically run different models? Do you put the same tasks to multiple models in parallel and compare the results? Or do you have a heuristic that model A is best for certain types of tasks and model B for others, etc?

I have found that recently I seem to just use deepseek for almost everything. It is just good enough and much much cheaper than everything else.

>> when do you typically run different models? Do you put the same tasks to multiple models in parallel and compare the results? Or do you have a heuristic that model A is best for certain types of tasks and model B for others, etc?

I am not sophisticated enough here. :-) I have just been following on experience and recommendations on HN.

>> I have found that recently I seem to just use deepseek for almost everything. It is just good enough and much much cheaper than everything else.

Will try it soon. :-)

Thanks.