Xi Chen (@chenxi17) 's Twitter Profile
Xi Chen

@chenxi17

ID: 377873822

calendar_today22-09-2011 07:56:47

92 Tweet

50 Followers

114 Following

Andrew D. Huberman, Ph.D. (@hubermanlab) 's Twitter Profile Photo

Most everyone that delays caffeine intake to 90-120min post waking experiences increased mood and energy (after the acclimation which takes 1-2 days), better afternoon energy and night time sleep. Caffeine timing matters.

Massimo (@rainmaker1973) 's Twitter Profile Photo

What a wagging dog tail really means: scientific data say that specific tail wags provide information about the emotional state of dogs [read more: buff.ly/2lv92q5] [📹: buff.ly/348gTnh]

Xi Chen (@chenxi17) 's Twitter Profile Photo

text-davinci-003 came up with a much better answer than chatGPT in this case, while text-davinci-002 completely missed the mark.

text-davinci-003 came up with a much better answer than chatGPT in this case, while text-davinci-002 completely missed the mark.
Xi Chen (@chenxi17) 's Twitter Profile Photo

Don't want chatGPT to hallucinate? Well, just ask! Also interestingly, text-davinci-3 doesn't know how to comply in this case, obviously the difference can only come from the additional human feedback when tuning the chatGPT.

Don't want chatGPT to hallucinate? Well, just ask! Also interestingly, text-davinci-3 doesn't know how to comply in this case, obviously the difference can only come from the additional human feedback when tuning the chatGPT.
François Chollet (@fchollet) 's Twitter Profile Photo

I don't think LLMs only solve "typing" (i.e. autocomplete). The way I see it, they solve a broad category of automation problems, where 1. The task medium is natural language 2. Many examples of the task were featured in the training data 3. You don't need >90% accuracy

(((ل()(ل() 'yoav))))👾 (@yoavgo) 's Twitter Profile Photo

can you explain LangChain to me? from the examples it seems that you have to learn a kinda-big api with many concepts, in order to replace straightforward, short and simple code. what am i missing here? what does it save?

Hao HONG 洪灝, CFA (@haohong_cfa) 's Twitter Profile Photo

Chinese went gaga over Messi yesterday. Argentina team uniforms swamped the streets. Mid game, this 15 y.o. broke all obstacles to hug Messi on the field. He quickly became a national sensation and a symbol of the pursuit of happiness in China.

François Chollet (@fchollet) 's Twitter Profile Photo

Human intelligence is most valuable as a kind of smart glue between many different humans and systems. Without culture, society, and outside technology, a single brain just can't do much.

Massimo (@rainmaker1973) 's Twitter Profile Photo

A sneaker wave is a disproportionately large coastal wave that can appear in a wave train without warning. [📹 Marcella Ogata-Day] x.com/Rainmaker1973e…

The Cultural Tutor (@culturaltutor) 's Twitter Profile Photo

These are the surprising origins of some of football's most famous kits and crests: From AFC Ajax being named after a mythical Greek warrior to Barcelona taking their club colours from a school in England...

These are the surprising origins of some of football's most famous kits and crests:

From AFC Ajax being named after a mythical Greek warrior to Barcelona taking their club colours from a school in England...
Massimo (@rainmaker1973) 's Twitter Profile Photo

This building in Fatih, Istanbul, Turkey is an excellent example of architectural styles stratification over the centuries. It shows three distinct periods: - Roman Byzantine Empire (bottom), - Ottoman Empire (middle), - Republic (three upper floors).

This building in Fatih, Istanbul, Turkey is an excellent example of architectural styles stratification over the centuries. 

It shows three distinct periods: 

- Roman Byzantine Empire (bottom), 
- Ottoman Empire (middle), 
- Republic (three upper floors).