LLM Misalignment Can be One Gradient Step Away, and Blackbox Evaluation Cannot Detect It.
Models that appear aligned under black-box evaluation may conceal substantial latent misalignment beneath their observable…
Author: AI News Team
Bridge Thinking and Wall Thinking
There are a couple of frames I find useful when understanding why different people talk…
Safe AI Germany (SAIGE)
TL;DR: SAIGE is a national research and field-building initiative, started in January 2026. We believe…
Self-Recognition Finetuning can Reverse and Prevent Emergent Misalignment
TL;DREmergent Misalignment (EM) is correlated with model identity, we find two pieces of evidence for…
Mini-Munich Succeeds Where KidZania Fails
This post is part of a larger exploration (not yet finished, but you can follow…
Optimal (And Ethical?) Methods To Find “Optimal Running”
Epistemic Status: The central quote of this essay is just pure slop, of course. But…
‘Staying with it’ Done Wrong
I was meditating today and noticed quite some over-effort happening. So I did the diligent,…
US Army announces contract with Anduril worth up to $20B
The Army described this as a single enterprise contract consolidating more than 120 separate "procurement…
Forecasting Dojo Meetup – postmortem discussion.
Hi Everyone, The next meetup of the forecasting practice group is here! Next week we're…
Meta reportedly considering layoffs that could affect 20% of the company
These layoffs could help Facebook's parent company offset its aggressive spending on AI infrastructure, as…