

Haven’t configured much beyond this but what’s wrong with ollama launch opencode <model>? Haven’t had an issue yet.


Haven’t configured much beyond this but what’s wrong with ollama launch opencode <model>? Haven’t had an issue yet.


Tomorrow’s a big day :D
Hell yeah! Loved the previous games. Didn’t fully understand the newest trailer but still super hyped for it.
Get out of here you weirdo /s


I want to get a steamdeck but I feel (felt?) I’m too late in so I figured I’d just wait for the second one…
The opposite for me: maruchan in a cup and nissin in stovetop. I also like the rhin ramyon but prefer the regular red spicy one (the OG).
git checkout mommy
Just donated! Best of lucks.


Holy crap TIL about open railway map. Thanks, I always was annoyed how google showed highways and not railways when you zoom out.


There’s a railway museum? Cool, I’ll be sure to visit it if I ever go back. Though your geoguess is a bit off as the pic was taken near pier 39 and the museum is close to the embarcadero no?


Yeah fair enough, it would be great.


Lmao a hyperloop? Hyperloops have enough problems in land between reasonably distanced places. This won’t happen.


Well, yes of course. Some relatives have few foreigner coworkers and they seem to be happy. (tho I don’t know them personally). Also I’ve met some foreigners through university and they seem to adapt well. But I guess it heavily depends on what kind of lifestyle you want to have.
People are usually warm and we appreciate it if you show interest in our culture and adapting here. You should be more than fine if you are mindful to that and better still if you are naturally outgoing. Good luck and hope you find a cool place to go, or things get better if you end up not moving.
Opencode with local inference (via ollama) Have tried gpt-oss-20b, qwen3.6-30somethingB and gemma4-e4b. Qwen is too slow for my hardware and gemma4 does not follow instructions that well. Haven’t spend much time (yet) but gpt-oss seems like a good balance.
For work I also use opencode but with either claude-opus or deepseek-v4-pro. Obviously opus is stronger, but deepseek is still surprisingly capable and I have more control (can’t figure out how to show opus reasoning traces) so I prefer it.
That said, I still write code myself 90% of the time. I just use llm for questions, codereview, etc.