←back to thread

Harper – an open-source alternative to Grammarly

(writewithharper.com)
645 points ReadCarlBarks | 1 comments | 20 Jun 25 19:51 UTC | HN request time: 0.238s | source
Show context
icapybara ◴[20 Jun 25 23:54 UTC] No.44333232[source]▶
Why wouldn't you want an LLM for a language learning tool? Language is one of things I would trust an LLM completely on. Have you ever seen ChatGPT make an English mistake?
replies(5): >>44333272 #>>44333473 #>>44334660 #>>44335861 #>>44339618 #
Groxx ◴[21 Jun 25 00:00 UTC] No.44333272[source]▶
uh. yes? it's far from uncommon, and sometimes it's ludicrously wrong. Grammarly has been getting quite a lot of meme-content lately showing stuff like that.

it is of course mostly very good at it, but it's very far from "trustworthy", and it tends to mirror mistakes you make.

replies(1): >>44334550 #
perching_aix ◴[21 Jun 25 04:37 UTC] No.44334550[source]▶
Do you have any examples? The only time I noticed an LLM make a language mistake was when using a quantized model (gemma) with my native language (so much smaller training data pool).
replies(1): >>44356339 #
1. Breza ◴[23 Jun 25 14:45 UTC] No.44356339[source]▶
Not GP, but I've definitely seen cutting edge LLMs make language mistakes. The most head scratching one I've seen in the past few weeks is when Gemini Pro decided to use <em> and </em> tags to emphasize something that was not code.