Mark Woodward @DataScienceMW

Data Scientist at SIL International | Machine Learning | NLP for low-resource languages. github.com/woodwardmw Oregon, USA Joined July 2021

Tweets

279
Followers

284
Following

510
Likes

1K

Jeremy Howard @jeremyphoward

a year ago

For those that hope (or worry) that LLMs will do breakthrough scientific research, I've got good (or bad) news: LLMs are particularly, exceedingly, marvellously ill-suited to this task. (if you're a researcher, you'll have noticed this already) Here's why🧵

103 515 4K 798K 3K

Towards Data Science @TDataScience

2 years ago

In a new deep dive, Rahul Nayak walks us through the process of building an AI research agent capable of answering questions about the intricate details within the Mahabharata, the longest epic poem ever composed. buff.ly/3L3e60W

0 3 12 5K 5

Mark Woodward @DataScienceMW

2 years ago

Realizing (again) how much more useful this app is if I switch to the Following tab. Posts from people I've chosen to follow, which only have a handful of likes and comments, are generally way more informative than posts with 10k likes which have been optimized for the algorithm.

0 0 0 90 1

Adam Azzam @AAAzzam

2 years ago

You can do constrained sampling in ChatGPT and micromanage its output. The catch? You only get one token. But you can do a lot with that one token. You can make it a classifier, a logic gate, or have it choose tools deductively. Here's how 🧵 From my talk this week @trychroma

5 26 133 14K 126

Yann LeCun @ylecun

2 years ago

MMS: Massively Multilingual Speech. - Can do speech2text and text speech in 1100 languages. - Can recognize 4000 spoken languages. - Code and models available under the CC-BY-NC 4.0 license. - half the word error rate of Whisper. Code+Models: github.com/facebookresear… Paper:…

163 1K 5K 1.6M 3K

Cristiano Giardina @CrisGiardina

2 years ago

Tired of waiting for GPT-4-32k? Bing Chat Creative Mode uses a GPT-4 model with a context window of ~13,500 tokens! Here's how you can use it & how I found this out!

18 115 972 473K 1K

Download Image

Sahil Patel @saaaahiiiil

3 years ago

I'm currently pursuing an MA in Linguistics from the University of Mumbai. We have a mandatory year long field linguistics course where every year, we try to document either an endangered or a lesser studied language. A few things I learnt from this course, a 🧵

12 40 362 39K 53

Mark Woodward @DataScienceMW

3 years ago

My Saturday afternoon project was going to be attempting to run Stable Diffusion via @modal_labs. It turns out it only took me 10 minutes, because they already have the code, and it was so straightforward...! modal.com/docs/guide/ex/…

2 8 49 6K 11

Mark Woodward @DataScienceMW

3 years ago

I enjoy doing the @0xbnomial machine learning question each day. I think this latest one must still have been in my subconscious last night, because I dreamed about it and had an insight in my sleep into a machine learning project I'm advising someone on! today.bnomial.com/?20230121

0 0 0 53 0

Mark Woodward @DataScienceMW

3 years ago

Today I learned that in Python the string '\n' has length 1, not 2...!

2 0 17 1K 0

Mark Woodward @DataScienceMW

3 years ago

I'd love to have an email assistant that not only helped me compose emails, but was fine-tuned on the thousands of emails that I've written so it could do so while sounding like me, rather than sounding like a generic English speaker.