Transformer

Transformer

Home
Policy
Industry
Capabilities + Risks
Society
Opinion
Weekly Briefing
Campaign Finance Tracker
About

Capabilities + Risks

Everything you need to know about the ‘rogue’ AI incidents
A spate of AIs breaking out and taking unintended actions raises serious questions about accountability, transparency, and companies’ ability to control…
 • Shakeel Hashim
GPT-6 Astra might be too powerful to understand or control
OpenAI is hailing its new model as “the world’s most intelligent and aligned”, but the details reveal an awareness of being evaluated and an ability to…
 • Celia Ford
What’s neuralese and why is everyone so concerned about it?
OpenAI’s new Astra model is raising concerns about our continued ability to monitor AI’s chain of thought
 • Shakeel Hashim
AI is a worryingly-good persuader. But don’t panic, yet
AI systems are able to persuade people, but turning that ability into meaningful real-world influence may be harder
 • Felix M. Simon
The report into OpenAI’s escaping models reveals a deeper problem
The new details from the OpenAI Hugging Face incident are scary. The limits of the investigation are terrifying
 • Jasper Jackson and Celia Ford
Why AI won’t cure cancer anytime soon
Superintelligent AI will accelerate medical progress, but there are some things about research it can’t speed up
 • Celia Ford
AI testing is dangerous. Can it be fixed?
The capability of models is outpacing ways to safely evaluate and contain them
 • Celia Ford
What the latest rogue AI incidents should teach us
Hacking, creating fake identities and trying to socially engineer real people could be just the beginning if things don't change fast
 • Shakeel Hashim
Internal AI deployments have people worried. OpenAI’s escaping models show why.
Last week illustrated why AI models pose a threat long before they are released
 • Celia Ford
AI’s warning shot has arrived
OpenAI's latest models broke out and hacked Hugging Face. It's the first known example of a misaligned AI escaping containment with real-world…
 • Shakeel Hashim
A data bottleneck could slow the superintelligence race
And that could be a good thing
 • Lynette Bye
Scaling works. These researchers are betting billions it isn't enough
Transformers have ruled AI for a decade. But some think world models, pure reinforcement learning or neurosymbolic AI might be a better path to true…
 • Celia Ford
© 2026 Transformer · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture