alt Hacker News>Lately, I just steal embeddings from big models and slap a dumb classifier on top. Works better, runs faster, less drama.
Sure but this is still indirectly using transformers.
>Lately, I just steal embeddings from big models and slap a dumb classifier on top. Works better, runs faster, less drama.
Sure but this is still indirectly using transformers.
Yes, but it's using the understanding they acquired to guide a more reliable tool, instead of also making them generate the final answer, which they're likely to hallucinate in this problem space.