91–100 of 128 posts
Earlier quoted context omitted.
> Microsoft sees everything Are you using Windows or Microsoft Office? Same here. Or Microsoft Exchange?
Source on Microsoft employees seeing everything I write in "Microsoft Office"? Not 365, but local docx
It is in fact Office 365 but the local application, not the cloud software, where you type into the browser.
Earlier quoted context omitted.
my comment will probably get flagged or downvoted or whatever, but yeah agreed. I literally cannot understand how people code that need gpt as an assistant for writing code. If I can reason about it, I can write it faster then the feedback loop takes for prompting.
I agree with your experience, and am curious as to what the difference between the two scenarios is.
Chatgpt as a debugging partner has been a adam and eve sort of match to me. It's a saviour!
- Debugging - I just throw 100s of lines of logs and it's pretty good at figuring out what needs to be done
- Landing page copy generation and iterations on that copy
- Summarizing papers
- Extracting insights from user feedback
- Improving emails, fixing grammar
And once I was done, asking it to write up some functions for the way they interact worked out very well.
In general, I've made a habit of asking it coding questions (usually how to do something in a complicated framework) before bothering teammates. Probably about 80% success rate.
A few directors have sent emails lettings folks know it's ok to experiment with as long as they dont send passwords or PII. I had it draft a thorny recursive SQL query for me one time (which I did write some extensive automated tests to validate)
Your directors are more creative than mine. Our CyberSecurity had ChatGPT non functional within days of it being released publicly. Apparently it's too much of a risk, or some nonsense.
We are a small team and those are just my use cases: - Debugging - I just throw 100s of lines of logs and it's pretty good at figuring out what needs to be done - Landing page copy generation and iterations on that copy - Summarizing papers - Extracting insights from user feedback - Improving emails, fixing grammar
How does that work, given the small context window size? I've tried dumping a lot of text into the ChatGPT window and it just ignores most of it, or complains about the input being too long.