Llamafile is a great way to get use an LLM locally. Inference is incredibly fast on my ARM macbook and rtx 4060ti, its okay on my Intel laptop running Ubuntu.
That link doesn’t work; I’ll assume it says that he was denied asylum because he committed fraud against an Australian citizen. This doesn’t really provide evidence that his claims of being a spy are false, only that he committed fraud in Australia. It’s definitely a point against his character, but not evidence that he lied about being a spy.
Since you aren’t interested in being skeptical of your sources and jumped on the first thing that seemed to match the narrative you were pushing I found some evidence for you. Oddly enough there’s an entire Wikipedia article about him that goes into pretty significant detail about why his claims of being a high level spy are probably false.
It’s odd that you didn’t see the Wikipedia article, I’m sure you have access to Wikipedia in your country don’t you?
The South China Morning Post said a man claiming to be a former Chinese spy was lying without providing any evidence? Well that’s good enough for me, thanks for busting this myth with all this evidence!
A simpler answer might be llamafile if you’re using Mac or Linux.
If you’re on windows you’re limited to some smaller LLMs without some work. In my experience the smaller LLMs are still pretty good as chat bots so they might translate well.
I love duckDB, my usual workflow is:
Then duckdb treats the directory just like a databese that you can build indexes on, and since they’re parquet files they’re hella small and have static typing. It was pretty fast and efficient before, and duckdb has really sped up my data wrangling and analysis a ton.
Should include “has duckplyr” which is bad ass in the few weeks I’ve been using it.
I have a soft spot for Jenkins because it was the first integration tool I ever used fresh out of college.
But today I want to stab the server because a job started failing randomly with a permission error when trying to copy a file.
I have a soft spot for Jenkins because it was the first integration tool I ever used fresh out of college.
But today I want to stab the server because a job started failing randomly with a permission error when trying to copy a file.
To be fair it’s a pretty terrible dataset. The AI is just going to say “this” to every question you ask
Every thing you google is just going to direct you to a link to let me google that for you
I love DuckDB. It’s really nice to be able to put a bunch of parquet files in a directory and then do operations on them as if they were a sql database. You can even put an index on the files if you’re feeling froggy.
If you’re doing a lot of reporting I highly recommend getting familiar with Quarto. It’s incredibly flexible for writing ad hoc reports, automated reporting, dashboards, presentations, etc. You can use python, R, observable, or Julia.