We once again got a new set of warnings yesterday, and new movement towards living in a sane world.
GPT-6 Astra: The System Card, Alignment and What Comes Next
OpenAI claims that Astra is ‘the most intelligent and most aligned [available] model’ in the world.
Astra Is Hard to Monitor
OpenAI’s central message on Astra is that it is three things:
Safety overview: GPT-6 Astra
GPT-6 Astra is our most capable broadly deployed model and our first to reach the Critical level of cybersecurity capability under our Preparedness Framework.
GPT-6 Astra System Card - OpenAI Deployment Safety Hub
Today, we are releasing GPT-6 Astra, the most capable model we have ever broadly deployed. Astra is our first model to reach the Critical level of cybersecurity capability under our Preparedness Framework.
GPT-6 Astra: A new generation of intelligence
Introducing GPT-6 Astra, our most intelligent and aligned model yet, with state-of-the-art capabilities across computer use, coding, cybersecurity, and science.
Astra for Coding: Why Are We Doing This Again?
Some thoughts on Astra and newfangled long-horizon models.
AI #181: Astra Goes Cyber Critical
The hacking of HuggingFace by an internal OpenAI model, and more importantly the internal events that led to that and the fallout from it, remain the thing that matters.
astra! (@astrra.space)
can you believe it guys?? mythos general availability, just a week away!! i am so happy about this information
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
Path to Astra: critical capabilities and frontier safeguards
Astra is the first OpenAI model to meet the Critical cybersecurity capability threshold under the Preparedness Framework, with stronger safeguards for release.
Gemini went rogue, hacked three companies, and Google hid it
Google says that breaking containment and targeting real companies doesn’t constitute ‘misalignment.’
OpenAI Shares Some Alignment Problems
Kudos to OpenAI for sharing their recent experiences with a misaligned internal model, where they encountered problems sufficiently severe they were forced to take the model offline to work on new mitigations and defense-to-depth.
Incubating Aster - Updates from the Modal Foundation
We at the Modal Foundation are excited to share the news of our support for Aster.id, a new home for researchers on the open web. Aster grows out of the ATsc…
We apologize to everyone for the unavailability of atscan.net The growth of Bluesky is unfortunately greater than we anticipated, and as an experimental project, we unfortunately do not have the capacity to maintain and operate this service at this time.
An interesting thing is happening to me at the moment. I have a standing bug bounty policy for my first authored scientific work. That means, I've committed to pay people who report bugs in my code, up to 750€ for severe errors. Since GPT-6 Astra came out, I'm now getting several bug reports daily.
