The forum
We've featured 165 posts from members, read by roughly 2,800 readers per week. These posts consist of anonymously submitted works written by students, and works suggested by students which are written by other authors.
All posts
The 'AI is a Bubble' Narrative is Stupid, Wrong, and Dangerous
Republished with permission by Devansh, writer of AI Made Simple. The situation is a bit… odd. OpenAI signs a $300B deal with Oracle. Oracle buys tens of billions in GPUs from Nvid…
Writing & Thinking with AI Assistance
This post was either an anonymous submission of an interesting paper or was written by a student; full credit remains with the author (linked). Part of a series on AI tools for em…
Inside the Black Box: A Practical Field Guide to Mechanistic Interpretability
Researchers argue that Mechanistic interpretability is the most effective technical strategy for ensuring AI alignment and safety. While traditional methods like reinforcement lear…
What My Students Had to Say About AI
Reposted with permission by Marcus Luther. Originally posted at the link referenced. Since there's also that pedagogical curiosity of mine—one that humbly recognizes that, at some …
An Interesting AI Conversation With My Students
At some point down the road I might try to pull together a full scope-and-sequence of the research path itself to share out, but for today's post I just wanted to highlight one int…
LLMs and World Models, Part 1
In the long-ago times, before large-scale generative AI came on the scene, machine-learning systems had some problems: often they didn't learn the general concepts we were trying t…
LLMs and World Models, Part 2
Perhaps the most widely cited evidence for emergent world models in LLMs is a pair of studies that focus on the simple board game Othello. This second installment examines research…
Do AI Reasoning Models Abstract and Reason Like Humans?
The Abstraction and Reasoning Corpus (now called ARC-AGI-1) has become popular as a test of abstract reasoning ability in AI models. This post summarizes new research examining whe…
The Largest School District in America Just Drew A Line on AI
Reposted with permission from Elissa Malespina. The largest school district in the United States has now released official guidance on artificial intelligence. That alone would be …
What Students Want Teachers to Know About AI
Reposted with permission from original author(s). Back in December I sat down with a handful of HS students on a couple different occasions to talk about AI — their thoughts, attit…
How Does Persistent Memory Affect AI Safety?
This post was submitted by a SAIRC member either as a recommended read or student-created post. All credit remains with the original author. Written with Maksym Andriushchenko, th…
In an AI World, What's the Work?
Reposted with permission from original author(s). More than a decade ago, immersed in research on competency-based education, I read Leaders of Their Own Learning, a comprehensive …
Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
This post was submitted by a SAIRC member either as a recommended read or student-created post. All credit remains with the original author. A security evaluation of the emerging …
AI Shouldn't Be Doing More Philosophy Than Students
Reposted with Permission from Mike Taubman and AI Waypoints. Last weekend I found out that AIs can now reincarnate. This got me thinking about both the high school juniors I teach …
MLSN #19: Honesty, Disempowerment, & Cybersecurity
This post was submitted by a SAIRC member either as a recommended read or student-created post. All credit remains with the original author. An issue of the ML Safety Newsletter, …
Write something yourself
- Tutorials or deep-dives on an AI topic
- A reframing: a new way of looking at something people think is settled
- Research results written in plain language
- Resources and opportunities you found (summer programs, tools, datasets)
- Thought experiments and ideas you have not finished thinking through
- Notes or study guides from a course you took
Send it through the form and we will put it up, usually within a few days. If you would rather just email it, sairc.support@gmail.com works too.