llwj

How efficient is it now? The last time I checked, FHE required minutes of computation and gigabytes of memory to store tiny amounts of data, and since it does not hold IND-CCA, I could not find any use cases.

Isn't the inline chat feature the same as Ctrl+I (https://code.visualstudio.com/assets/updates/1_79/copilot-ed...) in GitHub Copilot? I find it really useful, although the main page of GitHub Copilot does not appear to mention this feature.

Even GPT-3.5 can solve that on the first try. I didn't measure time but it should be within a minute. https://chat.openai.com/share/7f6a97de-9aef-49db-946b-15bfd9...

I'm curious about that too. Recently, I've seen many screencasts in the same style, and I hate them. The constant movement of the recorded area is quite distracting.

I see wrong responses about 1% of the time, but I love it, considering parsing raw text output without function calling had a much higher error rate.

The performance differences are so large (5x, 6x, and 18x faster) that I can't believe them. Is bun really faster on large codebases, not just on hello world?

> Do we have a bug in our updater or localization?

It can be done with error reporters like the "System program problem detected. Do you want to report the problem now?" popup in Ubuntu. In my experience, many users are willing to send error reports, and they're extremely useful, although 90% of reports are garbage.