| Website | https://www.sleepwalking.dev |
| GitHub | https://github.com/mitchwinn |
Mitch Winn
@mitchwinn
- 30 Followers
- 330 Following
- 29 Posts
iOS developer at Nike
@simonbs no problem!
@johnvoorhees not yet! I primarily use Claude Code along with Cursor and/or Xcode. I’m hoping swift assist can replace cursor at some point but lack of features like MCP support will hold that back.
@johnvoorhees It's a good start, but if you start to use it in your workflow you hit rate limits very quickly using the built in free version of ChatGPT.
@hunter Nice! This is all a bit of a moving target trying to find the exact words to do what you want. One thing I've learned from others regarding prompting, is to use AI to generate prompts for you. It works incredibly well and is what I did in this situation. It tends to know how to speak to itself!
@hunter here is a gist of the code as well https://gist.github.com/mitchwinn/8b2b0fe507c141b2e61e5e396c491030
@hunter Are you giving your LanguageModelSession instructions that tell it to be neutral? I quickly tried this and was successful summarizing a random politics focused article from NYTimes.
Here are the instructions I fed it:
"Please summarize the main points and key insights of the following news article in a concise and neutral manner. Focus on the essentiall details and avoid including opinions or speculative content. Keep the summary to one paragraph or less."
@hunter Ah yeah thats a bummer especially since it is just for summarization. I wonder if/when they allow us to use private cloud compute or other services if those guardrails will lessen. It would be a good question to ask to see if there is a way around it with the current APIs if you are attending the AI frameworks group lab later today!
@hunter Yeah I have hit those guardrail errors as well, but got around it if I tweaked my prompt to be more descriptive or just used different words. I wonder if that will improve through the betas to be more descriptive on what is actually happening when those errors are thrown.
@hunter Interesting, I assumed one of the benefits of a local model would be that you wouldn't have limits like that. I know there is a context limit, maybe that is what you are hitting but the error message is just worded weird.