My other favorite thing was talking to this one hvac company that only did x brand heat pumps(dont remember), but could not provide performance specs on them. The company couldnt either. Aside from "this one is really quiet!"
So i went with carrier, which had perfornance specs for all their equipment, at multiple different ambient and desired temps.
When i was trying to get a heat pump, i had to listen to a family friend hvac guy yell at me for 10 minutes cus he hates those damn things.
Yeah ive heard that too so I tried it but I think we prefer olive oil.
Ok its the external_directory permission. You set it in you opencode config json file. It should be in your home folders/.config
https://opencode.ai/docs/permissions
I just set "external_directory": "false" and that took care of it
I have a tub air fryer that i sometimes put oil in. Olive oil cooked french fries are really damn good.
Those sound like old models which doesnt help. Generally the best model in my experience is qwen3.6-27b. Ornith 9b is the smallest model ive used that is decent at tool use.
The attempting to write to the wrong folder can be helped by denying a permission in your config. Dont have it off the top of my head.
It is a good tool for coding. I could complain about data mining issues with non local stuff like claude... But what really bothers me is how some programmers dont even check its output. For work they get PAID to do. Im not even talking about not checking the code. They dont even check the product to see if it works or not. I have had 2 cases of this on freelance contracts so far.
Im fine with local only, but theres so many people that just vomit out exactly what claude says.
A lot of my grocery stores have pizza dough ready to go thats about $2.50 and can be frozen. So if you buy your ingredients and a pizza stone, you can have some REALLY good pizza any time.
I like to put the sauce on, then toast the crust for about 4-5mins before putting the rest on. Keeps the crust crispy.
Also, a dough ball isnt as hard to fit in the fridge.