There are incredible authors who happen to be dyslexic, and brilliant mathematicians who struggle with basic arithmetic. We don't dismiss their core work just because a minor lemma was miscalculated or a word was misspelled. The same logic applies here: if we dismiss the semantic capabilities of these models based entirely on their token-level spelling flaws, we miss out on their actual utility.

Treat LLMs as dyslexic when it comes to spelling. Assess their strengths and weaknesses accordingly.

Will that protect you from the agent changing the code to bypass those safety mechanisms, since the human is "too slow to respond" or in case of "agent decided emergency"?

Yes, and even holding couple of cartridges for different scenarios e.g image generation, coding, tts/stt, etc

There are so many use cases for small and super fast models that are already in size capacity -

* Many top quality tts and stt models

* Image recognition, object tracking

* speculative decoding, attached to a much bigger model (big/small architecture?)

* agentic loop trying 20 different approaches / algorithms, and then picking the best one

* edited to add! Put 50 such small models to create a SOTA super fast model