Is this just a Suno-wrapper?

Can you give an example that I can test with gpt-4-0314?

providing the seed would have allowed it to be shared

alas, I was overworked and underslept and forgot. my bad...

you can use negative logit bias

I switched to Cursor (VSCode fork) a couple of months ago. It does this already and I haven’t looked back since. Especially as the copilot extension (along with all my others) work out of the box.

It has full knowledge of your entire codebase rather than being limited to currently open files (I assume embeddings with RAG) and will index documentation (or any other URL).

I find it especially useful for things like Swift/SwiftUI APIs given how quickly they can evolve, not to mention copilot’s other limitations when it comes to languages beyond JS/TS, Python, etc

How can you be sure Cursor isn’t just pilfering your entire codebase? Where’s the trust factor? Does look cool tho

copilot recently added feature to "ask your codebase"

Wow huggingface is down completely

This is the nuanced insightful discussion I come to HN for

They use similar models to the codex models, they mentioned it a couple years ago

cushman and code-davinci are similar for sure (same architecture). Perhaps that's what they meant.

That’s what Stability AI has been doing… There are already open source LLMs the size of GPT-3 such as OPT and Bloom

No they haven't. Stability AI is funded by the founder and VC money, not crowdsourcing.

Why do your replies read like ChatGPT output

Let’s test that..:)