Salesforce is dialing back LLMs, leaning on deterministic automation and guardrails after reliability gaps. The aim: predictable outcomes, clean data, and no missed steps.
Upskill teams on data foundations, deterministic workflow design, and agent governance.
Or just don’t use a large token* model if you need reliability. Those models are probabilistic by design.
*no, I’m not calling them “language” models. Just like I’m not calling a taxidermised cat a “meow meow kitty fwiend”: it’s cringe as fuck and inaccurate.
Absolute layman question for you: is LLM really a marketing speak? I searched for “large token model” and it is absolutely buried under “large language model”, no other way for me to find out than to ask somebody knowledgeable.
I think it’s less of “marketing speak” and more of a general ignorance on what language is supposed to be, leaking into the marketing team. [With then me being the old man angrily screaming at the cloud, I guess.]
If you ask most people what language is, they’re talking about words. A few will talk about grammar (morphology and syntax), some about the raw material (sounds, characters, gestures). But the important part of a language is none of those. It’s meaning: we speak because we want to say something, everything else is just prep work.
And those models are really good emulating some layers of the language, like the morphology and syntax. But when it comes to meaning, they consistently shit bricks. It’s like they have the most visible part of the language, but what matters the most — just like a taxidermised critter.
So let’s call a duck a duck. If what they do the best is to identify and chain morphemes, they’re morpheme models. And since “morphemes” are called “tokens” in the jargon, “token models”.
Or just don’t use a large token* model if you need reliability. Those models are probabilistic by design.
*no, I’m not calling them “language” models. Just like I’m not calling a taxidermised cat a “meow meow kitty fwiend”: it’s cringe as fuck and inaccurate.
Absolute layman question for you: is LLM really a marketing speak? I searched for “large token model” and it is absolutely buried under “large language model”, no other way for me to find out than to ask somebody knowledgeable.
I think it’s less of “marketing speak” and more of a general ignorance on what language is supposed to be, leaking into the marketing team. [With then me being the old man angrily screaming at the cloud, I guess.]
If you ask most people what language is, they’re talking about words. A few will talk about grammar (morphology and syntax), some about the raw material (sounds, characters, gestures). But the important part of a language is none of those. It’s meaning: we speak because we want to say something, everything else is just prep work.
And those models are really good emulating some layers of the language, like the morphology and syntax. But when it comes to meaning, they consistently shit bricks. It’s like they have the most visible part of the language, but what matters the most — just like a taxidermised critter.
So let’s call a duck a duck. If what they do the best is to identify and chain morphemes, they’re morpheme models. And since “morphemes” are called “tokens” in the jargon, “token models”.