AI, C++, Rust, Pytorch, Software Developer, Calisthenics, Squat, Deadlift
Québec, Canada
Joined December 2009
- Tweets5.8K
- Following1.4K
- Followers1K
- Likes226
I read "Domain Expertise Has Always Been the Real Moat" brethorsting.com/blog/2026/0…
I am reading "AI Job Grief: The Unnamed Psychological Crisis Hitting Tech Workers" jackmaguire.org/blog/ai-job-…
ARC Prize 2024 Puzzle 0ca9ddb6 youtu.be/9d_mKu8mQqs?si=RaU3… via @YouTube
Rich Sutton’s new path for AI | Approximately Correct Podcast youtu.be/NvfK1TkXmOQ?si=L_f3… via @YouTube
The Bellman equation is all you need !
- en.wikipedia.org/wiki/Q-lear…
- en.wikipedia.org/wiki/Bellma…
- nature.com/articles/nature14…
- storage.googleapis.com/deepm…
#artificialintelligence
Sébastien Boisvert retweeted
Training with large minibatches is bad for your health.
More importantly, it's bad for your test error.
Friends dont let friends use minibatches larger than 32. arxiv.org/abs/1804.07612
All Time Warmest Barefoot Winter Boots – Zero Drop, Snow, & Waterproof anyasreviews.com/warmest-bar… #barefoot
ARC prize progress on puzzle 3aa6fb7a
arcprize.org/play?task=3aa6f…
github.com/sebhtml/Arc-Prize…
youtube.com/watch?v=7kMembVT… @arcprize #AI
Learning to solve the example 1 of puzzle 3aa6fb7a in the ARC prize @arcprize dskernel.blogspot.com/2024/1…
For the ARC price arcprize.org/, today I have increased the number of layers from 4 to 8. To do this on the NVIDIA A40 GPU on runpod.io/, I changed my batch_size from 1024 to 512 and changed num_layers from 4 to 8. #AI @arcprize
For the ARC price arcprize.org/, today I fixed a bug that caused my neural network to not see all the input text of a sample because the context was 140 characters but the samples were 211 characters
Sébastien Boisvert retweeted
You can tell the RL is done properly when the models cease to speak English in their chain of thought
