Opus 4.7 @ 7.5x is a joke. It's unusable and stops mid task and encounters more errors than any other premium model. #193157
Replies: 1 comment
-
|
💬 Your Product Feedback Has Been Submitted 🎉 Thank you for taking the time to share your insights with us! Your feedback is invaluable as we build a better GitHub experience for all our users. Here's what you can expect moving forward ⏩
Where to look to see what's shipping 👀
What you can do in the meantime 💻
As a member of the GitHub community, your participation is essential. While we can't promise that every suggestion will be implemented, we want to emphasize that your feedback is instrumental in guiding our decisions and priorities. Thank you once again for your contribution to making GitHub even better! We're grateful for your ongoing support and collaboration in shaping the future of our platform. ⭐ |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
🏷️ Discussion Type
Product Feedback
💬 Feature/Topic Area
Copilot in GitHub
Body
The most frustrating thing is the number of mistakes it makes, and I have to resend the message or send a new one, which then burns 7.5X times 1, 2 and sometimes 3. It can easily burn 45 prem reqs in one turn and not really produce anything noticeable over using gpt5.4.
@7.5X times (1-3) I would expect more stability and less tool calling errors, but it's worse.
I burned through 700 prem requests in 2 hours! and moved through 2 phases of my proj. (That same 700 could have easily got me through 10 phases in 3 projects in gpt5.4)
But I had to fully test it and paid my school fees.
So just to be clear, I didn't use it for coding. I was using it as my agent that produces the coding task plans and review plans. Pure strategy and it only needs to write a 50-100 line docs... after 8 docs, 700 prem reqs gone...
Boooo! 🤑
Beta Was this translation helpful? Give feedback.
All reactions