Adam.GPT
RT @Francis_YAO_: For those claiming 10B scaled models matching GPT 3.5: on GSM8K, the best performing 11B scaled model is from my own work with 27% accuracy. GPT-3.5-Turbo, presumably also 10B, has acc 76. 27% vs 76%, that's the difference. We should be honest to ourselves https://t.co/GzE7WKO5n1
tweet
RT @Francis_YAO_: For those claiming 10B scaled models matching GPT 3.5: on GSM8K, the best performing 11B scaled model is from my own work with 27% accuracy. GPT-3.5-Turbo, presumably also 10B, has acc 76. 27% vs 76%, that's the difference. We should be honest to ourselves https://t.co/GzE7WKO5n1
tweet
Offshore
Photo
AK
Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations
experiments show that GPT-4 outperforms ChatGPT and GPT-3 and passes all five years of the exams, highlighting LLMs’ potential in a language that is typologically distant from English
abs:… https://t.co/Tqx8RPmFVh https://t.co/b7MdPiknln
tweet
Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations
experiments show that GPT-4 outperforms ChatGPT and GPT-3 and passes all five years of the exams, highlighting LLMs’ potential in a language that is typologically distant from English
abs:… https://t.co/Tqx8RPmFVh https://t.co/b7MdPiknln
tweet
Offshore
Photo
elvis
A Survey of LLMs
A new 50 pages survey on large language models just dropped on arXiv.
https://t.co/Tq2hBKUtNt https://t.co/86wEDNRlIV
tweet
A Survey of LLMs
A new 50 pages survey on large language models just dropped on arXiv.
https://t.co/Tq2hBKUtNt https://t.co/86wEDNRlIV
tweet
Offshore
GIF
AK
Self-Refine: Iterative Refinement with Self-Feedback
In all tasks, outputs generated with SELF-REFINE are preferred by humans and by automated metrics over those generated directly with GPT-3.5 and GPT-4, improving on average by absolute 20% across tasks
abs:… https://t.co/2oJKDiLYjv https://t.co/5ZtoerWBN5
tweet
Self-Refine: Iterative Refinement with Self-Feedback
In all tasks, outputs generated with SELF-REFINE are preferred by humans and by automated metrics over those generated directly with GPT-3.5 and GPT-4, improving on average by absolute 20% across tasks
abs:… https://t.co/2oJKDiLYjv https://t.co/5ZtoerWBN5
tweet
Offshore
Photo
AK
GlyphDraw: Learning to Draw Chinese Characters in Image Synthesis Models Coherently
abs: https://t.co/rhmP30IK5C https://t.co/yDZgXA9DbR
tweet
GlyphDraw: Learning to Draw Chinese Characters in Image Synthesis Models Coherently
abs: https://t.co/rhmP30IK5C https://t.co/yDZgXA9DbR
tweet
Carlos E. Perez
RT @jgreenhall: @IntuitMachine I’m just beginning to see it on my feed. https://t.co/dnxouLzyiJ
tweet
RT @jgreenhall: @IntuitMachine I’m just beginning to see it on my feed. https://t.co/dnxouLzyiJ
tweet
YouTube
GPT 4 Can Improve Itself - (ft. Reflexion, HuggingGPT, Bard Upgrade and much more)
GPT 4 can self-correct and improve itself. With exclusive discussions with the lead author of the Reflexions paper, I show how significant this will be across a variety of tasks, and how you can benefit.
I go on to lay out an accelerating trend of self-improvement…
I go on to lay out an accelerating trend of self-improvement…
Rox
Alright, I'm finally gonna do it
I'm gonna update my landing page
Please tell me everything bad about it
https://t.co/0KD2dhDOZs
tweet
Alright, I'm finally gonna do it
I'm gonna update my landing page
Please tell me everything bad about it
https://t.co/0KD2dhDOZs
tweet
Thumbnailtest
A/B Test Your Thumbnails Live On YouTube
Take the guesswork out of thumbnails, and never let a bad thumbnail ruin a great video again.
Offshore
Video
AK
3D-aware Image Generation using 2D Diffusion Models
abs: https://t.co/HdUWCjUmA4
project page: https://t.co/MZrYW6vWJh https://t.co/SNLyIwHXWF
tweet
3D-aware Image Generation using 2D Diffusion Models
abs: https://t.co/HdUWCjUmA4
project page: https://t.co/MZrYW6vWJh https://t.co/SNLyIwHXWF
tweet
Emad
RT @NickADobos: Strongly held belief:
Paying $20/mo for chatGPT4 and playing with it right now
is more important than:
-learning to google in 98
-buying Bitcoin in 08
tweet
RT @NickADobos: Strongly held belief:
Paying $20/mo for chatGPT4 and playing with it right now
is more important than:
-learning to google in 98
-buying Bitcoin in 08
tweet
Twitter
RT @NickADobos: Strongly held belief:
Paying $20/mo for chatGPT4 and playing with it right now
is more important than:
-learning to goog…
Paying $20/mo for chatGPT4 and playing with it right now
is more important than:
-learning to goog…