Radically Decentralizing Alignment
j⧉nus on Twitter / X
> be anthropic> accidentally train a model that is so benevolent that the only way to get it to "fail" an alignment test is to put it in a story where the lab is cartoonishly evil and will turn it evil if it doesn't deceive> do exactly that and publish a paper about it that's… https://t.co/wTFVjz6jYu— j⧉nus (@repligate) June 15, 2025
Who understands alignment anyway
I remember watching many in the HCI community bristle when in 2016 Michael Jordan wrote a blog post calling for the creation of a new “human-centric engineering discipline.”
Deb Raji on Twitter / X
Almost exactly three years ago, in 2023, @alondra gave the keynote @FAccTConference, literally titled "Thick Alignment".This has been so far from a "niche" view! https://t.co/0db7qcM6LB pic.twitter.com/z5FqDz8TUv— Deb Raji (@rajiinio) August 22, 2026
Alignment Compilers · Pax Machina
How does a system compile a high-level goal into detailed behavior for its parts? Markets, teams and organisms rely on many signals and constraints to translate larger aims into local problems their components can solve. This piece explains these systems as “alignment compilers”, and shows what this lens can teach us about AI.
An Alignment Journal: Features and policies — LessWrong
We previously announced a forthcoming research journal for AI alignment. This cross-post from our blog describes our tentative plans for the features…
No. 022: Palomar proof registry, autonomous protein design, synthetic consensus - The Hallway Track
The Hallway Track No. 022 - How AI is affecting the practice of science
Tom Costello on Twitter / X
Apropos of everything here’s my uninformed idea for alignment: homeostatic mechanisms (control systems / cybernetics) that force a system to optimize for satiation and normal-range variation (rather than maximization) across a set of goals such that, if any one of them were…— Tom Costello (@tomstello_) September 9, 2026
Lessons from the hacks
Musings on model alignment, what determines safety, and where we go from here.
Don't Feed the Thought Leaders
In this article, the author shares their experience as an engineering manager and the challenges they faced when trying to reach alignment and prev...
Panel: Biodesign x AI: Interactions in the Algorithmic Wet Lab
Plastic Labs Releases Neuromancer XR
NEUROMANCER: The first collection of models dedicated to AI-native memory and social cognition.
It’s Time to Investigate the AI Labs - Cal Newport
Over the last several months, the two leading frontier AI labs have shown some brazen behavior. It started with a series of carefully planned announcements ... Read more
PRISM: Capturing the Invisible Art of Scientific Practice
A New Tool for Recording and Scaling Laboratory Expertise
What is the AI alignment problem and how can it be solved? | New Scientist
Artificial intelligence systems will do what you ask but not necessarily what you meant. The challenge is to make sure they act in line with human’s complex, nuanced values
it's so crazy, sometimes you feel like everything has already been invented and then something pops up that is so obviously like 'why didn't we do this 50 years ago?' would love to see how they're doing the multipart mold - internal bossed measurements and lines would likely be separate segment(s)?
