nicognaw

OpenAuthJs is literally a hono app.

Users in these kind of platforms usually do welcome English posts according to some experience with Xiaohongshu, but registering an account from outside is challenging.

If you got random tokens on Apple Silicon Macs, you should check your stderr for Metal’s error code, like 5 for out of metal memory. Metal lets you use half of your unified memory as metal memory.

Andrej made the micrograd video after the code was released a couple years later. As someone who takes learning neural networks as a hobby, I really want to see him make videos about the llama.c project.

Azure OpenAI

As learned by the community, they leaked their personal information from emails used in git commits

+1, the OpenAI official playground & the new fine-tuning UI are really useful stuff, but surprising enough, I don't find open source versions.

Why would I use drag-and-drop UIs to replace one of my favorite things, coding, when I use infrastructure as code stuff to replace a cloud console panel, FastAPI to generate OpenAPI documents, and even D2-lang to draw graphical diagrams?

In some US states where TikTok is banned, this can be used to access it.

Jina AI itself is also a great framework to expose APIs from deep neural net models and deploy them to Kubernetes clusters, which I think is very promising, but they didn't get as much hype as I predicted that they deserved.

Signoz is too good at SEO.

Early days, I looked up otel and observability stuff, and I always saw Signoz articles on the first screen.

TL;DR: Cheap GPU cloud with alpaca-LoRA

Maybe a bit extreme, but I am going to use Remix and only Remix for my new side projects.

I'm actually very excited to see AI applied in games in ways other than AI agents.

As a developer, I'd like a tool to help me design the color scheme for my IDE, and I'm curious if this one can do that.

Prompt engineering, in my opinion, could be considered "semantic programming."

Since LLMs generate words one by one, you can only determine whether the next word has a high probability. Some ideas occurred to me earlier, like applying prompt engineering to evaluate if the model is confident about the contents to be generated.

Like "Please reply T if you are confident about the text that you are going to generate, and F if you are not".

But if this could be done by architecting the neural networks, they would perform much better.

I'm learning the basics of transformer from Andrew Ng's courses, your post seems to make me learn it faster. Thanks!

Why not? The actual work that language models do is to complete the conversation. It doesn’t actually answer questions, it just tries to make the text look real.