To be fair, you'd have to also import this crate to get the result he wanted:

https://docs.rs/unicode-segmentation/latest/unicode_segmenta...

'girl math'? really? It's literally a bunch of old men and always has been.

Isn't it quite possible they replaced that Flash model with a distilled version, saving money rather than increasing quality? This just speaks to the value of open-weights more than anything.

Who says you need to use a top model to produce cybersecurity slop? Did this person use o3?

https://hackerone.com/reports/3125832

Running the 3 bit quant of https://huggingface.co/unsloth/Qwen3-235B-A22B-GGUF now on a 128GB macbook.

Those sound like the sort of issues which could be caused by your server silently truncating the middle of your prompts.

By default, Ollama uses a context window size of 2048 tokens.

I checked this, the whole conversation was about 1000 tokens.

I suspect the Ollama version might have wrong default settings, such as conversation delimiters. The experience of Gemma 3 in AI studio is completely different.

Evidently they simply aren't respecting the .gitignore when choosing which file contents to post to their servers, https://forum.cursor.com/t/env-file-question/60165/9

Regardless of whether it actually makes a commit with the secret, it's still being leaked.

> As someone who is actually friends with Brad Pitt on Facebook and have given him money

Are you telling us you fell for the same pig butchering scam?

I thought my over-the-top response made it clear it was satire and a comment on the absurdity of someone thinking they're "actually friends with Brad Pitt and he needs my money"

Is there a difference anymore?

Good point, it’s already practically impossible to distinguish between ChatGPT o1 output and say the median substack essay. At least for someone who only has a few minutes to spare for second guessing.

really makes you wonder what Babbage was trying to achieve with his Difference Machine...