Тёмный

Testing Frontier LLMs (GPT4) on ARC-AGI 

ARC Prize
Подписаться 892
Просмотров 1,4 тыс.
50% 1

Template: www.kaggle.com/code/gregkamra...
arcprize.org/leaderboard
arcprize.org/arc-agi-pub
ARC Prize is a $1,000,000+ public competition to beat and open source a solution to the ARC-AGI benchmark.
Hosted by Mike Knoop (Co-founder, Zapier) and François Chollet (Creator of ARC-AGI, Keras).
--
Website: arcprize.org/
Twitter/X: / arcprize
Newsletter: Signup @ arcprize.org/
Discord: / discord
Try your first ARC-AGI tasks: arcprize.org/play

Опубликовано:

 

26 июн 2024

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 11   
@LimeTubeH
@LimeTubeH 2 дня назад
I'm confused...what are we supposed to attach with our API add-on secret?
@ARCprize
@ARCprize 2 дня назад
What do you mean attach? That’s where you put your API key and then reference it in your code
@MarkoTManninen
@MarkoTManninen 3 дня назад
I understand retries, but I am confuced with the two attempts. Do you always need to provide two? In which case they would have different data and both would be required for 100% correct prediction? I also missed the part in which the prediction and correct answers are matched and prounounced.
@ARCprize
@ARCprize 3 дня назад
Sorry this isn't more clear on the video! You get two tried at each task. Old competitions had 3 tries. So you can basically give two attempts. If either are correct you pass the task. Under scoring methodology there is more information: arcprize.org/guide#submissions
@conformist
@conformist 4 дня назад
first.
@cyb3rvoid
@cyb3rvoid 4 дня назад
That was unreal!
@conformist
@conformist 4 дня назад
@@cyb3rvoid for my next magic trick, i will solve the agi price first
@wwkk4964
@wwkk4964 4 дня назад
​@@conformistsolve it backwards!
@filipgara3444
@filipgara3444 4 дня назад
Ensure diversity in your model
@aluphshahim5808
@aluphshahim5808 4 дня назад
Second 😂
Далее
Could AI solve this puzzle? (ARC-Game)
18:42
Просмотров 3,1 тыс.
Improving LLM accuracy with Monte Carlo Tree Search
33:16
How Cohere will improve AI Reasoning this year
1:00:23
Просмотров 12 тыс.
Explore ARC-AGI Data + Play
11:03
Просмотров 3,7 тыс.
NEW TextGrad by Stanford: Better than DSPy
41:25
Просмотров 8 тыс.
I wish every AI Engineer could watch this.
33:49
Просмотров 58 тыс.
ARC PRIZE - Win $1Million to Beat the ARC-AGI benchmark
13:47
Has Generative AI Already Peaked? - Computerphile
12:48