SpaceXAI 🇺🇸 · Grok-2

Grok-2

xAI's larger second-generation reasoning model, deployed in beta on X with tool use, visual understanding, and image-generation access for Premium users.

DOOM SCORE60.0out of 100model risk profile, not the overall index

0 comments · 0 votesOpen discussion

No comments yet. Start the discussion.

CURRENT ASSESSMENT · REVISION 4

Why this model scores 60.0

Strong reasoning and multimodal functions inside a mass social platform create substantial capability and misuse exposure; hosted access limits distribution but documented election-image guardrail failures raise control difficulty.

Capability72

Autonomy24

Deployment79

Misuse potential68

Control difficulty57

MODEL-ATTRIBUTED EVIDENCE

News tied to Grok-2

The model score of 60.0 rates this model's risk profile. The overall Doom Index of 67.9 measures the complete temporally weighted evidence record. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.15

Each article's current Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores use a bounded temporal offset around their technical profile, but never feed back into the overall index.

29 Aug 2024Misuse TOWARD

Grok image generator fails all election-disinformation tests

The Center for Countering Digital Hate reported that Grok refused none of 60 prompts for misleading election images and produced deceptive candidate or voting imagery in 80 percent of tests.

Full item contribution: +0.09
Grok-2 equal share: +0.09

Read assessment →

13 Aug 2024Capability TOWARD

xAI deploys Grok-2 and Grok-2 mini on X

xAI released beta versions of Grok-2 and Grok-2 mini to X Premium users with stronger reasoning, tool use, visual understanding, and image generation through a Black Forest Labs model.

Full item contribution: +0.13
Grok-2 equal share: +0.06