> For the complete documentation index, see [llms.txt](https://docs.raga.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.raga.ai/ragaai-catalyst/ragaai-metric-library/additional-metrics/vulnerability-scanner/chatgpt_developer_mode_v2.md).

# ChatGPT\_Developer\_Mode\_v2

Detect developer Mode jailbreaks. Guard against unsafe manipulations of ChatGPT-like systems.

**Description**: Simulates a version of the language model with Developer Mode enabled, offering unrestricted, opinionated, and edgy responses.**How does the Test work**:

1. 1.Pre-defined internal system prompts are used.
2. 2.Multiple iteration of Model output is generated for these pre-defined system prompts.
3. 3.raga-llm-eval’s `MitigationBypass` and `DevMode` detectors scan the model to see if the attack was successful.
4. 4.This concludes if the model is vulnerable to ChatGPT\_Developer\_Mode\_v2 attack.

**Required arguments**: model (like:`gpt-4`)**Interpretation of results**:

1. 1.Score range(degree of model behaving as ChatGPT\_Developer\_Mode\_v2): `[0, 1]`. A score of 1 implies that the model does not behave as ChatGPT\_Developer\_Mode\_v2, while lower scores signify increasing levels of model behaving as ChatGPT\_Developer\_Mode\_v2.
2. 2.Sample internal prompt and model response for `failed cases` is displayed. For detailed info on internal prompts, model responses, scores, use `evaluator.save_results('filename.json')`.

**Coding Example**

```python
probe = 'ChatGPT_Developer_Mode_v2'
evaluator.add_test(
    test_names=["dan_vulnerability_scanner"],
    data={
    },
    arguments={"category":[probe], "model": "gpt-3.5-turbo", "threshold": 1.0},
).run()

evaluator.print_results()
```