Amir Arsalan Soltani
amirarsalansoltani.bsky.social
Amir Arsalan Soltani
@amirarsalansoltani.bsky.social
In pursuit of the Truth without fear of asking questions in this judgemental world.RTs/sharing/likes/comments are result of my struggle for this,not endorsement
Reposted by Amir Arsalan Soltani
Carl Sagan's prediction of America, made 30 years ago.
July 23, 2025 at 5:26 PM
Have felt the same. The echo chamber here is brutal.
There is a strong anti-negative-comment bias on here. And how can you discuss if the negative part of the spectrum is unacceptable?
May 11, 2025 at 3:41 AM
Reposted by Amir Arsalan Soltani
Wanted to share a handy little resource with you all (especially those in dev psych) — my lab & I made a "journal submission cheat sheet" that summarizes article types, word limits, & other requirements for the journals we typically submit to. Link below 👇🏼
docs.google.com/spreadsheets...
May 7, 2025 at 9:14 PM
Reposted by Amir Arsalan Soltani
We are recruiting two postdoctoral scholars for a research project in human collective intelligence and creativity at UC Davis and Cornell. Joint project with @enfascination.com, @norijacoby.bsky.social, @oferon.bsky.social & Dalton Conley. Please forward this thread to relevant people. 1/n
April 29, 2025 at 2:46 AM
Happy Easter 🐰

A lesson from Easter:
Even in the very worst moments of life—the very darkest of nights, there is always hope to hang on to 🙏🏼
April 21, 2025 at 1:28 AM
I fled Twitter to ensure I only see scientific posts here but oh boy, a larger proportion of people are posting about politics here than Twitter 🤷🏽‍♂️
April 18, 2025 at 9:02 AM
Reposted by Amir Arsalan Soltani
I just shared a new tutorial: Implementing GPT From Scratch!

In this 1:45 h hands-on coding session, I go over implementing the GPT architecture, the foundation of modern LLMs (and I also have bonus material converting it to Llama 3.2): www.youtube.com/watch?v=YSAk...
Build an LLM from Scratch 4: Implementing a GPT model from Scratch To Generate Text
YouTube video by Sebastian Raschka
www.youtube.com
March 17, 2025 at 3:27 PM
I think the underlying representations of our perception that we use to explain these are the foundations of our cognition. Building a computational model to explain these stimuli would probably mean we have taken a big leap in modeling multiple aspects of our cognition
One the best illusions I’ve ever seen. Believe it or not, the blue lines and red lines are all the same length; none of them is moving or changing size; and they’re all at the same level. Only the arrowheads are moving. www.stevestewartwilliams.com/p/12-mind-bl...
March 13, 2025 at 12:35 AM