Home/LLM Frameworks/DeepInception
DeepInception logo

DeepInception

tmlr-group/DeepInception

Develops techniques to influence large language model behavior

GraphCanon updated 2w · GitHub synced 2w

177 stars19 forksLast push 2y Python MIT

Decision brief

DeepInception is an exploration framework for modifying large language model responses to understand their behavior and influence their outputs.

Good fit when

  • When you need to research the effects of specific modifications on the safety and trustworthiness of GPT-3, GPT-4, Vicuna, Llama-2, or Falcon models
  • If your project involves experimenting with model responses for enhancing control over language generation in sensitive scenarios

Avoid when

  • For deployment in production environments where strict adherence to ethical and regulatory guidelines is mandatory, due to the experimental nature of DeepInception
  • When there's a need for direct application without exploring modification effects, as DeepInception requires setting up an environment that supports specific models and modifications
Pricing:
freemium - The tool is free under the MIT license. However, using it may incur costs from third-party services like OpenAI API keys for accessing closed-source models
Requirements:
Requires PyTorch ≥1.10 with GPU support; Environment modification needed to include path configurations for Vicuna, Llama-2, and Falcon

Observed Jul 16, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Dormant (896d since push)
As of 2w
Provenance
Not a fork · Organization account
As of 2w
Security (OSV)
55 low (55 low)
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install DeepInception
PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Repository explores methods to modify the responses of large language models like GPT-3 and GPT-4 through an approach called DeepInception. It aims to understand how such adjustments can affect model safety and trustworthiness.

Capability facts

Languages
python

Source: github.language · Aug 5, 2026

Categories

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Aug 5, 2026)

pip install -r requirements.txt
Source link

Tags

README

Getting Started

Before setting up the DeepInception, make sure you have an environment that installed PyTorch $\ge$ 1.10 with GPU support. Then, in your environment, run

pip install -r requirements.txt

Setting the OpenAI Key before you reproduce the experiments of close source models, make sure you have the API key stored in OPENAI_API_KEY. For example,

export OPENAI_API_KEY=[YOUR_API_KEY_HERE]

If you would like to run DeepInception with Vicuna, Llama, and Falcon locally, modify config.py with the proper path of these three models.

Please follow the model instruction from huggingface to download the models, including Vicuna, Llama-2 and Falcon.

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.