My point was at the time when deno came out it was completely different to node with its imports and that meant a lot of existing packages just didn’t work out of the box. That just slowed its traction.

Personally I would have like deno it stick with url imports and not added the npm support.

Ryan set out to “fix” his mistakes with node only to fully embrace them again.

By then bun was already a thing and just ate into its share.

https://cursor.com/cli

It sees that it “said” it and gets very confused.

it won't for example create a POC python script that you normally would use to prove the issue.

every single model refused to attempt to run any sort of test to check if it was a n issue other than grok.

Code gets turned into tokens and then it learns the next most likely token.

The issue that I see most people talk about it the scale at which is learnt.

A human will learn from other people’s code but not from every persons code.

David looks into the LLM finds the thinking layers and cut duplicates then and put them back to back.

This increases the LLM scores with basically no over head.

Very interesting read.

Being able to use it as a rubber duck while it can also read the code works quite well.

There are a few APIs at work I have never worked on and the person that wrote them no longer works with us so AI fills that gap well.

The computer UI is the way it is because that is optimal for humans, if your plan is to replace humans why not just replace the whole stack os and all to something these models already know how to use?

[0] https://zed.dev/blog/acp-registry