←back to thread

My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)

(simonwillison.net)
577 points simonw | 1 comments | 29 Jul 25 13:45 UTC | HN request time: 0.001s | source
Show context
h-bradio ◴[29 Jul 25 16:07 UTC] No.44725090[source]▶
Thanks so much for this! I updated LM Studio, and it picked up the mlx-lm update required. After a small tweak to tool-calling in the prompt, it works great with Zed!
replies(1): >>44726075 #
torarnv ◴[29 Jul 25 17:27 UTC] No.44726075[source]▶
Could you describe the tweak you did, and possibly the general setup you have with zed working with LM Studio? Do you use a custom system prompt? What context size do you use? Temperature? Thanks!
replies(1): >>44739924 #
1. h-bradio ◴[30 Jul 25 21:51 UTC] No.44739924[source]▶
Here is how my prompt ended up! https://gist.github.com/hbradio/2f504c3fdb6f7113181b2d8c6862... I just asked an LLM to make it similar to a working Qwen prompt.

To make the LLMs able to use tools, I had to configure them in the Zed settings like this: https://gist.github.com/hbradio/fa4b456658a8d250e6ccc69ae9b3...

Also, I had to go into LM Studio and increase the max context size for each model I wanted to use in Zed. Otherwise it gives a parsing error on the response. I set it to the max allowable value.

I start LM Studio, start the LM Studio server, then go to Zeds AI config and tell it to connect to LM Studio. I put it in Agent mode, and it seems to work!

I don't know much about temperature, and I didn't use any other system prompt.

Good luck!