Hacker News new | past | comments | ask | show | jobs | submit login

It's good at writing new code, with sufficient prompting. But the big open question as of now for engineering orgs is - can it edit existing code like developers, just by instructions. Is there any hands on experience anyone has on copilot-x?



Copilot without -x does this relatively well. But it's a hands-on process. I can't just give it some source files and say "go". But it can easily make you 10x. I often spend more time tab-completing than writing.


I'm still trying to figure out how to do this. Copilot is extremely helpful. But more often than not, it suggests completions which would steer the project in another direction.

It is extremely good once the code has been organised and an overall structure exists. But until then it can be a distraction.


It helps me to create thoughtful docstrings and comments which directs the copilot to much stronger completions


How are you guys enjoying copilot? For me, it wastes time so often. It blocked my editor auto importing functionality and times where I really have some easy suggestion that I need, maybe 50% of the time it doesn’t suggest the right thing.

I’m hopeful for -x version though.


"steers the project in a different direction" Man, it can't read minds still?

Literally unusable.


I'm sorry but that's just too hard to believe. Even if it was a perfect reasoning/coding engine the fact that it's context is so limited guarantees it will get stuff wrong.

I'm a fan of copilot - but no way in hell is it a 10x tool. It's probably 1.2x - which is a huge gain for such a cheap tool.


Any publically available demos?

I've only played around with faux pilot and it seemed that it was mostly limited by my prompting skill.

Also, is copilot aware of anything outside of currently edited file?


60 day free trial not enough for you?


GPT-4 32k can fit a few thousand lines of code into a single prompt and output diff's, patches, and/or the fully modified code.

For best results, pasting any relevant documentation into the prompt can help.


Is there word of ane outside big co's getting access to 32k ?

I got 8k access pretty quickly but no word whatsoever about 32k (and my current prompts + context already reach 8-9k tokens)


GPT-4 32k access is being rolled out widely now: https://news.ycombinator.com/item?id=35841460

Btw, a line of code is around 7-8 tokens. So you can fit over 4,000 LoC in the context window.


I'm paying for chatgpt. How can I tell what input token size I get?


It's 4k, both for GPT4 and for GPT 3.5.


Are you paying for API access or for ChatGPT plus?


32k is on Azure


Can you demo it, please?




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: