good: tough tests bad: - course materials not available as pdf - nothing on algorithmic efficiency, scaling laws or emergence ugly: - w1: it's not said that it focuses on causal language models, 2nd exercise lacks method signature, smoothing not explained - w2: limitation of perplexity to causal language models not explained (cfr https://huggingface.co/docs/transformers/perplexity) - w3: sound quality, free article instead of nyt (https://arstechnica.com/tech-policy/2023/06/lawyers-have-real-bad-day-in-court-after-citing-fake-cases-made-up-by-chatgpt/), rlhf follows fine-tuning

A really good course, especially the first two weeks. The third week is also okay, but completely different and not very technical. The course is a bit rough around the edges: a few quiz questions are ambiguously formulated and the Python notebooks sometimes have typos. Still, a good course to learn about language models and to some get hands-on experience.

I want to gain hands-on experience with GPT rather than knowing the things mentioned in Module 3. The whole course is a waste of time! I'd rather take other courses!

Good course overall. The video explanations could be a little more in-depth. And I think they could explore more labs than dedicating the entire last week to non-technical questions, or plus one more week maybe.

I liked the course, It was informative with a little of coding assignments. The coding assignments could be a bit more in depth.

Great overview of GPT with some labs and very recent information. Deep Learning training is recommended.

Excellent !!!

get into more details of transformers models

Lots of gaps and code mistakes and little to no discussion.