Meh. That’s nothing compared to the amount of curation and tuning the LLMs are coerced with.
No--even a really tiny, underpowered model like GPT-2 with no system prompt produces coherent (though not necessarily desirable or correct) responses.
alt Hacker News
No--even a really tiny, underpowered model like GPT-2 with no system prompt produces coherent (though not necessarily desirable or correct) responses.