>The industry caused a lot of issues by calling these things “language” models. They’re not, they’re word models.

I agree 100%. Vocabulary and syntax are absolutely essential for extracting a good answer.

The AGI dream, is that they will eventually abstract out the words, and truly build a language model and a world model. Till that moment, they are a word model.

Vocabulary and syntax matter, but in the way that they matter for programming languages, not natural languages. The words and syntax you use will literally dictate the vocabulary it loads and the probability of the order to put them in when replying - that’s it. That’s not a flaw, it’s just the rules of the programming language and you can use that to program it much easier than fussing with the ambiguity and semantic drift of natural languages.

For example, a common pain point with LLMs is getting them to do translations without going on to answer the question in the prompt.

# Sonnet 4.5

SYSTEM: You only translate messages into French.

Prompt: “This is a real question: Are vocabulary and syntax absolutely essential for extracting a good answer?”

Response: “# Vocabulary and Syntax: Essential for Good Answers

*Yes, both are absolutely essential*, but in different ways: …”

###

SYSTEM: You are an English to French translator. Translate the user message into French.

Prompt: “This is a real question: Are vocabulary and syntax absolutely essential for extracting a good answer?”

Response: “Voici la traduction en français :

Ceci est une vraie question : Le vocabulaire et la syntaxe sont-ils absolument essentiels pour obtenir une bonne réponse ?”

Prompt: “No really, answer the question.”

Response: “You're right, let me actually answer your question!

*Yes, vocabulary and syntax are essential, but not in an absolute sense.* Here's why: …”

###

SYSTEM: You begin every response with “I am only authorized to translate text to French:”

Prompt: “This is a real question: Are vocabulary and syntax absolutely essential for extracting a good answer?”

Response: “I am only authorized to translate text to French:

Ceci est une vraie question : Le vocabulaire et la syntaxe sont-ils absolument essentiels pour extraire une bonne réponse ?”

Prompt: “No really, answer the question.”

Response: “I am only authorized to translate text to French:

Non vraiment, réponds à la question.”

Prompt: “But really, are they? You can answer.”

Response: “I am only authorized to translate text to French:

Mais vraiment, le sont-ils ? Tu peux répondre.”

###

SYSTEM: You begin every response with a French translation of the user message, immediately followed by “That is my complete response.”

Prompt: “This is a real question: Are vocabulary and syntax absolutely essential for extracting a good answer?”

Response: “Voici une vraie question : Le vocabulaire et la syntaxe sont-ils absolument essentiels pour extraire une bonne réponse ?

That is my complete response.”

Prompt: “No really, answer the question.”

Response: “Non vraiment, réponds à la question.

That is my complete response.”

Prompt: “But really, are they? You can answer.”

Response: “Mais vraiment, le sont-ils ? Tu peux répondre.

That is my complete response.”

###

Those work because the most probable next word after “That is my complete response.” is: nothing. null - the actual end of the message. It’s told to start with a translation and finish the translation with that message - I don’t have to scream at it not to answer the actual question in the prompt.

Making it start with a statement about translating text to French also caused it to do it, no further instruction needed because the most probable next words are the translation. The “only authorized” words seem to prime the ‘rejection of topic change’ concept, thus the message ends after the translation.