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:
- Tutorials or deep-dives on AI topics
- Fresh perspectives: reframings or new ways of looking at something
- Novel research results communicated in plain language
- Resources and opportunities in AI (summer programs, tools, datasets)
- Thought experiments and speculative ideas
- Notes or study guides from courses
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…
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…
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…
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 …
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 …
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 …
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…
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…
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 …
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…
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…
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…
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…
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 …