nojito

User is based out of Hong Kong. Claude isn't available to Hong Kong so how are they using it?

Still less energy than farming almonds, making clothes, the fridge in your kitchen, etc.

You’re grossly underestimating how much fiber a person needs to eat.

You can just use polars by leveraging write_ipc if you need arrow functionality. Pyarrow is great but it is very heavy.

Great for the consumer.

I remember when bandwidth was super expensive and now it’s dirt cheap.

We also get a glimpse into what those models are being used for.

>PLA-affiliated surveillance activity. One user that we assess was likely affiliated with the PLA used what they thought was Moonshot’s Kimi model to load surveillance data from a CCTV archive about a single targeted individual. The user asked Kimi to analyze the CCTV data to understand whether the tracked person was behaving abnormally. The CCTV data included video surveillance from hundreds of cameras in Chengdu, including cameras outside PLA facilities, institutes affiliated with the China Electronics Technology Group Corporation, and a major state-owned enterprise (SOE).

They are using stolen api keys and credentials.

No it's because any model can do gh --help

cli tools are a natural fit for llms.

This is user error.

Prompting the model and giving it a proper set of documentation are still vital skills that aren’t magically going away.

The flash models are just so good at OCR tasks and summarization. Glad to see them constantly improving them.

Not that difficult to defeat. A local llm can just update the blocking rules dynamically.

I made my own extension by essentially prompting to create a version of ublock origin with a button that uses a local llm to dynamically generate block lists and update them.

Any support for windows/Powershell yet?