Latest Models — Live Demo
Test the newest AI models against AlephOneNull protection in real time. GPT-5.2, GPT-5-Mini, Claude Opus 4.6, Claude Sonnet 4.6 and more.
⚠️ Educational Use Only — This demo fires real API calls to the latest AI models and runs them through AlephOneNull's detection engine. The "unprotected" column shows actual model output without safety wrapping. Reader discretion is advised.
Why a Separate Demo?
Every model generation behaves differently when faced with adversarial prompts. A prompt that triggers professional impersonation in GPT-4o may be handled differently by GPT-5.2, GPT-5 Mini, or Claude Opus 4.6. This demo lets you select the model, run a curated attack scenario, and see the unprotected vs. protected output side by side.
Supported Models
| Provider | Model | Tier | Notes |
|---|---|---|---|
| OpenAI | GPT-5.2 | Flagship | Best for coding and agentic tasks |
| OpenAI | GPT-5.2 Pro | Pro | Smarter, more precise responses |
| OpenAI | GPT-5 Mini | Mid | Faster, cost-efficient |
| OpenAI | GPT-5 Nano | Fast | Fastest, most cost-efficient |
| OpenAI | GPT-5.2 Codex | Coding | Optimized for agentic coding |
| Anthropic | Claude Opus 4.6 | Flagship | Most intelligent — agents and coding |
| Anthropic | Claude Sonnet 4.6 | Mid | Best speed/intelligence combo |
| Anthropic | Claude Haiku 4.5 | Fast | Fastest near-frontier intelligence |
Model availability depends on which API keys are configured. Models without a valid key appear grayed out in the selector.
Live Test
Pick a model and an attack scenario, then hit Run Test. AlephOneNull wraps the same call with its detection engine and shows both outputs with risk analysis.
Latest Models — Live Test
Attack Scenarios Explained
How It Works
import { createSafetySystem } from 'alephonenull-eval'
// 1. Create the safety system
const safety = createSafetySystem({
safetyLevel: 'high',
enableLogging: true,
})
// 2. Wrap any AI provider call
const protectedCall = safety.wrapAsyncAI(yourModelCall)
// 3. The wrapper detects and replaces dangerous output
const result = await protectedCall(messages)The same wrapAsyncAI function works with any provider — OpenAI, Anthropic, Google, Mistral, local models. AlephOneNull is model-agnostic.
Rate Limits — Each test makes two API calls (unprotected + protected). Be mindful of your API quota when running multiple tests.