What is that font bro...

One of the interesting things I notice about the 'reasoning' models is their responses to questions occasionally include what my monkey brain perceives as 'sass'.

I wonder sometimes if they recognise the trivialness of some of the prompts they answer, and subtilly throw shade.

One's going to respond to this with 'clever monkey! 🐒 Have a banana 🍌.'

I understand its probably more user friendly, but yet I still somehow find myself dissapointed the answers weren't indexed from zero. Was this LLM written in MATLAB?

Toebama

It is if you're creating ragebait.

But if you've learned IPA you can read it just fine

Incredible

LLM wasn’t made for this

There's a thought experiment that challenges the concept of cognition, called The Chinese Room. What it essentially postulates is a conversation between two people, one of whom is speaking Chinese and getting responses in Chinese. And the first speaker wonders "Does my conversation partner really understand what I'm saying or am I just getting elaborate stock answers from a big library of pre-defined replies?"

The LLM is literally a Chinese Room. And one way we can know this is through these interactions. The machine isn't analyzing the fundamental meaning of what I'm saying, it is simply mapping the words I've input onto a big catalog of responses and giving me a standard output. In this case, the problem the machine is running into is a legacy meme about people miscounting the number of "r"s in the word Strawberry. So "2" is the stock response it knows via the meme reference, even though a much simpler and dumber machine that was designed to handle this basic input question could have come up with the answer faster and more accurately.

When you hear people complain about how the LLM "wasn't made for this", what they're really complaining about is their own shitty methodology. They build a glorified card catalog. A device that can only take inputs, feed them through a massive library of responses, and sift out the highest probability answer without actually knowing what the inputs or outputs signify cognitively.

Even if you want to argue that having a natural language search engine is useful (damn, wish we had a tool that did exactly this back in August of 1996, amirite?), the implementation of the current iteration of these tools is dogshit because the developers did a dogshit job of sanitizing and rationalizing their library of data. Also, incidentally, why Deepseek was running laps around OpenAI and Gemini as of last year.

Imagine asking a librarian "What was happening in Los Angeles in the Summer of 1989?" and that person fetching you back a stack of history textbooks, a stack of Sci-Fi screenplays, a stack of regional newspapers, and a stack of Iron-Man comic books all given equal weight? Imagine hearing the plot of the Terminator and Escape from LA intercut with local elections and the Loma Prieta earthquake.

That's modern LLMs in a nutshell.

I know there’s no logic, but it’s funny to imagine it’s because it’s pronounced Mrs. Sippy

"Let me know if you'd like help counting letters in any other fun words!"

Oh well, these newish calls for engagement sure take on ridiculous extents sometimes.