Discussion

Forum

The SAIRC Discussion Forum is a space for AI enthusiasts to share what they're thinking about. No formal research paper required. Posts can be submitted anonymously and span a wide range of formats:

Recent Posts
(When) Is Mechanistic Interpretability Identifiable?
I recently finished a paper, "Characterizing Mechanistic Uniqueness and Identifiability Through Circuit Analysis," alongside a group of three others and a mentor. This post discuss
Imran Kutianawala·February 14, 2026
Painless Activation Steering (PAS): Automated, Lightweight Post-Training for LLM Behavior
Reproduced with permission from Sasha Cui We're releasing "Painless Activation Steering (PAS)," a fully automated approach to steer large language models after training—without mo
Sasha Cui·February 14, 2026
Would a Language Model Push You Off A Bridge? Pt. 2
Utilitarianism, to recap, is a consequentialist decision-making framework which states that the best actions produce the most 'pleasure' for the greatest number of people. Deontolo
Imran Kutianawala·December 2, 2025
How to Use Deep Learning for Flood Forecasting
Reposted with permission from Devansh. Following is an excerpt from my article, "How Google Built an Open Source AI to Provide Accurate Flood Warnings for 460 Million People." The
Devansh ·December 1, 2025
What is Concept Drift and How to Solve It
Reposted with permission from Devansh. Thanks to their versatility, Neural Networks are a staple in most modern Machine Learning pipelines. Their ability to work with unstructured
Devansh ·November 11, 2025
Would a Language Model Push You Off A Bridge?
In the context of this post, 'utilitarianism' is a consequentialist decision-making framework which operates under the idea that the best action produces the most pleasure for the
Imran Kutianawala·November 5, 2025
Comparison of Convolutional & Feed-Forward Architectures on MNIST Digit Classification
I was unable to use Google Colaboratory for quite a bit, so it took me much longer than necessary to make this post. However, I'm finally able to log back in! This is the experimen
Meileen Song·October 8, 2025
A 20/80 Rule for AI in Education
Reposted with Permission from Mike Taubman and AI Waypoints. Yesterday my students used AI for 10 minutes. That was more than enough, in both senses. I teach a class for 11th and 1
Mike Taubman·October 2, 2025
The Convolutional Neural Network
The last few posts I've written about AI consciousness and infinite suffering have been fairly dire, so I decided to switch things up and write about something more practical: the
Evan Jafri·September 11, 2025
AI Consciousness: A Biological Perspective
Most policy debates about AI revolve around its potential upsides: whether AI as an augmented decision-maker can solve existential risks like climate change or pandemics. But a dif
Alyssa Cheung·August 14, 2025
Autoregression & Next-Token Prediction
Every time a language model generates text, it's doing something surprisingly simple: predicting one token at a time, with each choice shaped by everything that came before. This p
Imran Kutianawala·July 17, 2025
The Difficult Margins of AI as a Teacher
Reposted with permission from Marcus Luther and The Broken Copier. 'Do you know the meaning of logistics?' This is the opening quote from one of my all-time favorite scenes from on
Marcus Luther·June 25, 2025
The Sentence That I'm Very Tired Of Hearing as a Teacher
Reposted with permission from Marcus Luther and The Broken Copier. For the past year, there has been one sentence that I feel like I cannot escape. No matter where I look as a teac
Marcus Luther·March 12, 2025
Yes, Teachers, You Should Be Panicking About AI
Reposted with permission from Marcus Luther and The Broken Copier. In our final unit of the previous school year, I introduced our multi-genre projects—in which students are asked
Marcus Luther·December 10, 2022
Previous1234