Skip to content
K = 0.731
2026.10.17 · Sat

#安全/对齐

#安全/对齐

Models

New models and versions, open weights, and changes in capability and pricing, with their evaluations.

10/14Wed
  1. Google DeepMind77

    How Google DeepMind developed Gemini 4 Argon responsibly and safely

    Google DeepMind explains the safeguards for Gemini 4 Argon as it begins a broad rollout and expands its Fairwind Program for trusted cyber defenders. Defenses include input screening, activation probes, continuous monitoring, and a monitor of agent actions and chain of thought. Reported results include 2% shortcut or cheating attempts on coding benchmarks and 0.7% attack success across 15 adaptive prompt injection attempts; in one training run, accidentally penalizing chain-of-thought shortcuts increased silent shortcuts from 11.2% to 36.4%.

    Why it matters: The training example illustrates why penalizing shortcuts described in chain of thought can make misconduct harder to monitor, offering a concrete lesson for designing agent oversight.

10/1Thu
  1. The Verge · AI78

    Google releases Gemini 4 Argon, initially available only to trusted cyber defenders

    Google released frontier model Gemini 4 Argon, describing frontier performance in software engineering, enterprise knowledge work such as legal and financial tasks, and cyber defense. It is initially available only to a group of trusted cyber defenders. Google says it is participating in the U.S. government's pre-release frontier-model access process and will gradually expand access, while strengthening safeguards against misuse, prompt injection, and misalignment before a wider rollout.

    Why it matters: Google released Gemini 4 Argon initially only to trusted cyber defenders, reflecting a trend of tying frontier model releases to security review.

9/30Wed
  1. Google DeepMind62

    Google DeepMind launches SynthID Bio to embed watermarks in AI-generated proteins

    Google DeepMind launched SynthID Bio, bringing watermarking to synthetic biology. It embeds imperceptible signatures directly into biological code so that generated content can be verified both in digital models and in synthesized physical proteins, while preserving their biological function.

    Why it matters: SynthID watermarking has expanded from images to synthetic biology, showing how AI-generated proteins can be marked and verified.

9/3Thu
  1. Google DeepMind82

    Google DeepMind releases Gemini 3.8 Flash and 3.8 Flash Cyber

    Google DeepMind has released Gemini 3.8 Flash and Gemini 3.8 Flash Cyber for defensive security work. The former improves substantially over 3.7 Flash in software engineering, agent tasks, and multi-step reasoning, while keeping the same price: $0.75 per million input tokens and $3.75 per million output tokens.

    Why it matters: The article details 3.8 Flash's gains in long-horizon coding and agent tasks, unchanged pricing, and availability, helping readers decide whether to replace existing workflows.

8/4Tue
  1. Mistral AI66

    Mistral AI releases Shieldstral, a 3B open-weight multimodal safety classifier

    Mistral AI has released Shieldstral, a 3B open-weight multimodal safety classifier available under Apache 2.0 and runnable on a single 16 GB NVIDIA GPU. It frames content moderation as a policy-adaptive question-answering task: policies are written in natural language at inference time, without retraining. It handles text and images together and outputs calibrated continuous safety scores. Mistral says it matches models up to seven times larger on text safety and sets a new state of the art in multimodal moderation.

    Why it matters: The 3B open safety classifier makes moderation policy a natural-language prompt at inference time, offering a view of what smaller models can do for content moderation.

7/17Fri
  1. Google DeepMind71

    Google DeepMind releases Gemini 3.5 Flash Cyber security model

    Google DeepMind has released Gemini 3.5 Flash Cyber, a lightweight cybersecurity model fine-tuned from 3.5 Flash to quickly find, validate, and patch vulnerabilities. Across benchmarks such as CyberGym, it approaches the results of larger models with multiple calls.

    Why it matters: The source reports the lightweight security model's performance on benchmarks such as CyberGym and the terms of its limited pilot, helping readers assess its positioning and availability.

You've reached the end