Подтвердите e-mail

Для публикаций, комментариев, реакций и сообщений подтвердите адрес.

Публикация

Предыдущая публикация

i'm not even sure LLMs are fit for that purpose. jolt.law.harvard.edu/digest/retri... the framing of this article ("RAGs are good!") is frontloaded by a ton of writing about how specifically awful LLMs are. tldr LLMs are awful at this kind of work. amusingly i got this from an LLM proponent!

Retrieval-augmented generation (RAG): towards a promising LLM architecture for legal work?The above image is sourced from Wikimedia Commons. Generative artificial intelligence (AI)’s first encounter with the legal world was a catastrophe. After OpenAI released ChatGPT in Fall 2022 and the....jolt.law.harvard.edu
5152

my opinion is that legal work is the key indicator of whether LLMs are workable as research tools. this is the key area where such a tool, if it works, would be invaluable. tech is more tolerating of jank, for good and bad reasons. with legal work, well, you can't patch a contract.

Обсуждение

0 прямых ответов

Показаны не все ответы

Публичный счётчик показывает 1, а источник передал 0. Остальные ответы могли быть удалены, скрыты или не выданы публично.

Ответов пока нет

Обсуждение ещё не началось.