opus. only the best!
148 karma · joined September 14, 2022
From my early tests this seems like the first API alternative to GPT4. Huge!
Hopefully os models can catch-up to gpt4 in the next six months when we fixed all the low hanging fruit outside of the model itself
It feels like there are a lot of well-intended AI coding products that just don't pay attention to getting the details right. I actually started building my own extension recently, with an emphasis on getting all the little things right, because I got so frustrated at Copilot. Things like closing brackets properly, not interrupting me and destroying my train of thought when writing comments, not suggesting imports unless it's highly certain (or verified with intellisense), etc. Like why am I wasting my precious time talking to copilot chat with gpt3 when gpt4 exists?
It's still a pretty early version, and ultimately we're using the same underlying model for completion, but I think getting these details right make a huge difference (at least to my biased self).
If you want to try it: https://marketplace.visualstudio.com/items?itemName=doublebo...
You'll need to install the pre-release version for auto-complete.
I actually ended up starting usedouble.com (GPT3 for spreadsheets) to automate a lot of the work Magic was doing, as it felt quite expensive to have a human do those rote tasks. It often requires less verification as well, as the assistants often can make mistakes because they are not culturally familiar with the target task. For example, we used them to categorize a bunch of grocery products, and would see mistakes like putting frozen naan in the bakery section (where in north america grocery stores you'd expect that to be in the Frozen section). So it's interesting how GPT3 actually ends up being more accurate for things like this.
Note: I'm the founder :) Happy to answer any questions.
Reply below with some sample data/problem and I'll reply with a demo to see if we can solve it out of the box!