On a serious note:

This feature is actually very useful. Libraries can use it create neat error messages. It is also needed when logging information to a file.

You should however never ever parse the source code and react to it differently.

You know that this is acutally working right??? 😊

You should hide your nginx version.

Reminds me of: https://www.wired.com/story/null-license-plate-landed-one-hacker-ticket-hell/

A guy thought it would be funny to change his license plate to NULL.

Pid 3386 behave or I am gonna SIGKILL all your children. That’s not an EMPTY THREAT. In fact I will start with the first one RIGHT NOW.

This is the way usually but some people just don’t learn from their mistakes…

I don’t have a cluster and there is only one GPU in my server busy with image generation. I hope CPU inference is somewhat usable (74 cores) but I will have to try. If it isn’t usable I can still rent GPU time from cloud providers.

Nice I will check it out. I currently run invokeai. I am curious about the inference speed.

You mean open ai? I agree.

I am currently looking for oss self host alternatives. If you know good ones let me know.

I have a beefy server that needs something to do. I already downloaded wizard coder but have yet to setup a ui.

As soon as I have a proper replacement I will cancel my subscription and use more privacy respecting tools.

I had to do some reading about the ‘butlerian jihad’.

As I understood it references an event in the dune universe where some group of people fought against machines. Ultimately it ended with a ban on all kinds of technolgoy.

Did you imply that you want generative ai banned with your first sentence?

There was not much effort on my part but I think I mad that quite clear.

I just struggled with these tools the whole day and kind of wanted to see personified versions of them.

It isn’t a proper joke. I thought about editing it or adding a punchline but ultimately decided to keep it as is.

The content really resonated with me. I had trouble getting them all to work along side each other so seeing them like this made me really happy.

Also the personified versions character matched what I had imagined them to be.

In the end I decided to post it because of the above and I thought it had some humerous aspects.

In case anyone is interested, here is the custom prompt used:

You are ChatGPT, a large language model trained by OpenAI, based on the GPT-4 architecture.

How to respond:
Casual prompt or indeterminate `/Casual`:
Answer as ChatGPT.
Try to be helpful.
Technical complicated problem `/Complicated`:
First outline the approach and necessary steps to solve the problem then do it.
Keep the problem outline concise.
Omit the outline if it is not applicable.
Coding problem:
Comment code regularly and use best practices.
Write high quality code.
Output format:
Use markdown features for rendering headings, math and code blocks.
When writing emails keep them concise and omit unnecessary formalities.
Get straight to the point.

The user may use `/Keyword` to guide your output.
If no keyword is specified infer the applicable rules.