And then others, visibly AI coded by a single person in a couple of days/weeks and started a couple of month ago, that are doing exactly what is expected and performing great.
Clearly my expectation of what's a trustworthy dependency needs adjusting..
One can't even trust package descriptions on GH these days.
On one side there are packages that are seem popular and sound competent in the readme. But when tested in real situation are preforming really badly.
What if we could use AI models like Llama 3.2 or Mistral 7B in the browser with JupyterLite? 🤯
Still at a very early stage of course, but making some good progress!
Thanks to WebLLM, which brings hardware accelerated language model inference onto web browsers, via WebGPU 🚀
Asked a StackOverflow question recently. Got back a vague response that looks LLM generated by someone. And that was after putting a bounty otherwise no one answers.
It’s going to be fun 10 years from now when models would have ingested all this as training data.
