← Toutes les offres
Z

GPT-6.2 Astra and Sol: The System Card

Zvi

Global
Publié le 21 novembre 2026

Description du poste

We have to stop meeting like this. Alas, we will keep meeting like this. It is time, once again, to do the reading. As per usual, I will focus on things to the extent they are new and important. There are a lot of things that need to be in the system card in case something goes wrong, but that look exactly the way you would expect. I did my best to skip those. I continue to be on vacation. I am aware that via Claude there is now a claimed Lean proof of the Reimann Hypothesis and will cover that next week. Astra 6.2 Self-Portrait Table of Contents • Safety Overview (1). • Internal Deployment (1.2). • Preparedness Assessment (2). • Biological Threats (2.1.1). • Cyber Threats (2.1.2). • AI Self-Improvement Threats (2.1.3). • OpenAI Epoch Capabilities Index (OECI). • Safeguards (2.2). • AI Self-Improvement Threat Modeling (2.2.1.3). • Safety Training and Evaluation (2.2.2). • Jailbreak Robustness (2.2.3 and 2.2.6). • Realtime Model Safeguards (2.2.4). • Distillation Safeguards (2.2.5). • Security Controls (2.2.9). • Model Safety and Behavior (3). • Alignment and Monitorability (4). • Don’t Help Peer (4.1.5). • Verbalized Metagaming and Oversight Gaming (4.1.6). • Misaligned! (As Found By UK AISI) (4.1.7.1). • Astra is Hard to Monitor (4.2). Safety Overview (1) They start with the highlights. • Our evaluations show that GPT-6.2 Astra and GPT-6.2 Sol are the most capable models we’ve released for cybersecurity tasks. • To be expected. • GPT-6.2 Astra is our first externally released model to meet the High threshold for AI Self-Improvement. • In terms of underlying capabilities? Also to be expected. • Kudos to OpenAI for admitting this rather than dodging. • OpenAI took steps to heighten monitoring and check alignment. They are not nothing. I do not expect they would be enough if it mattered most. • Both models performed similarly to GPT-6 Astra on most alignment evaluations, particularly those measuring agentic workloads, but were more likely to omit known ob