Best AI tools for< Ai Safety Engineer >

The Frontier Model Forum (FMF) is a collaborative effort among leading AI companies to advance AI safety and responsibility. The FMF brings together technical and operational expertise to identify best practices, conduct research, and support the development of AI applications that meet society's most pressing needs. The FMF's core objectives include advancing AI safety research, identifying best practices, collaborating across sectors, and helping AI meet society's greatest challenges.

The Center for AI Safety (CAIS) is a research and field-building nonprofit based in San Francisco. Their mission is to reduce societal-scale risks associated with artificial intelligence (AI) by conducting impactful research, building the field of AI safety researchers, and advocating for safety standards. They offer resources such as a compute cluster for AI/ML safety projects, a blog with in-depth examinations of AI safety topics, and a newsletter providing updates on AI safety developments. CAIS focuses on technical and conceptual research to address the risks posed by advanced AI systems.

Anthropic is an AI safety and research company based in San Francisco. Our interdisciplinary team has experience across ML, physics, policy, and product. Together, we generate research and create reliable, beneficial AI systems.

MAIHEM is an AI-powered quality assurance platform that helps businesses test and improve the performance and safety of their AI applications. It automates the testing process, generates realistic test cases, and provides comprehensive analytics to help businesses identify and fix potential issues. MAIHEM is used by a variety of businesses, including those in the customer support, healthcare, education, and sales industries.

Athina AI is a platform that provides research and guides for building safe and reliable AI products. It helps thousands of AI engineers in building safer products by offering tutorials, research papers, and evaluation techniques related to large language models. The platform focuses on safety, prompt engineering, hallucinations, and evaluation of AI models.

Robust Intelligence is an end-to-end security solution for AI applications. It automates the evaluation of AI models, data, and files for security and safety vulnerabilities and provides guardrails for AI applications in production against integrity, privacy, abuse, and availability violations. Robust Intelligence helps enterprises remove AI security blockers, save time and resources, meet AI safety and security standards, align AI security across stakeholders, and protect against evolving threats.

AEye is a leading provider of software-defined lidar solutions for autonomous applications. Our 4Sight Intelligent Sensing Platform provides accurate, reliable, and real-time perception data to enable safer and more efficient navigation. AEye's lidar products are designed to meet the unique requirements of automotive, trucking, and smart infrastructure applications.

Faculty AI is a leading applied AI consultancy and technology provider, specializing in helping customers transform their businesses through bespoke AI consultancy and Frontier, the world's first AI operating system. They offer services such as AI consultancy, generative AI solutions, and AI services tailored to various industries. Faculty AI is known for its expertise in AI governance and safety, as well as its partnerships with top AI platforms like OpenAI, AWS, and Microsoft.

Robust Intelligence is an end-to-end solution for securing AI applications. It automates the evaluation of AI models, data, and files for security and safety vulnerabilities and provides guardrails for AI applications in production against integrity, privacy, abuse, and availability violations. Robust Intelligence helps enterprises remove AI security blockers, save time and resources, meet AI safety and security standards, align AI security across stakeholders, and protect against evolving threats.

Anthropic is an AI safety and research company based in San Francisco. Our interdisciplinary team has experience across ML, physics, policy, and product. Together, we generate research and create reliable, beneficial AI systems.

Voxel's Safety Intelligence Platform revolutionizes EHS by providing visibility, insights, and actionable security measures for industries such as Food & Beverage, Retail, Logistics, Manufacturing, and Ports & Customs. The platform empowers safety and operations leaders to make strategic decisions, enhance workforce safety, and drive efficiency through real-time site visibility, custom dashboards, risk management tools, and a sustainable safety culture.

OpenAI Strawberry Model is a cutting-edge AI initiative that represents a significant leap in AI capabilities, focusing on enhancing reasoning, problem-solving, and complex task execution. It aims to improve AI's ability to handle mathematical problems, programming tasks, and deep research, including long-term planning and action. The project showcases advancements in AI safety and aims to reduce errors in AI responses by generating high-quality synthetic data for training future models. Strawberry is designed to achieve human-like reasoning and is expected to play a crucial role in the development of OpenAI's next major model, codenamed 'Orion.'

MIRI (Machine Intelligence Research Institute) is a non-profit research organization dedicated to ensuring that artificial intelligence has a positive impact on humanity. MIRI conducts foundational mathematical research on topics such as decision theory, game theory, and reinforcement learning, with the goal of developing new insights into how to build safe and beneficial AI systems.

Imbue is a company focused on building AI systems that can reason and code, with the goal of rekindling the dream of the personal computer by creating practical AI agents that can accomplish larger goals and work safely in the real world. The company emphasizes innovation in AI technology and aims to push the boundaries of what AI can achieve in various fields.

Fordi is an AI management tool that helps businesses avoid risks in real-time. It provides a comprehensive view of all AI systems, allowing businesses to identify and mitigate risks before they cause damage. Fordi also provides continuous monitoring and alerting, so businesses can be sure that their AI systems are always operating safely.

Aify.co is a website that covers all things artificial intelligence. It provides news, analysis, and opinion on the latest developments in AI, as well as resources for developers and users. The site is written by a team of experts in AI, and it is committed to providing accurate and up-to-date information on the field.

Storytell.ai is an enterprise-grade AI platform that offers Business-Grade Intelligence across data, focusing on boosting productivity for employees and teams. It provides a secure environment with features like creating project spaces, multi-LLM chat, task automation, chat with company data, and enterprise-AI security suite. Storytell.ai ensures data security through end-to-end encryption, data encryption at rest, provenance chain tracking, and AI firewall. It is committed to making AI safe and trustworthy by not training LLMs with user data and providing audit logs for accountability. The platform continuously monitors and updates security protocols to stay ahead of potential threats.

Nuro is an autonomous technology company focused on revolutionizing mobility through robotics and AI. They offer cutting-edge AI-first autonomy solutions for automotive and mobility applications, including robotaxis and autonomous vehicles. Nuro's state-of-the-art AV technology, Nuro Driver™, is designed to drive safely and naturally on all roads using groundbreaking AI-first autonomy. The company prioritizes safety in all aspects of its operations, from hardware and software to testing and systems engineering. With 8 years of autonomy innovation, Nuro aims to transform the way goods and people move by empowering fleets with AI-first autonomous capabilities.

viAct.ai is an AI-powered construction management software and app that utilizes computer vision and video analytics for workplace safety. The platform offers scenario-based AI vision technology to simplify monitoring processes, automate construction management, and enhance safety measures on construction sites. viAct.ai has been recognized for its innovative technology and has received several awards for its contribution to the construction industry.

bottest.ai is an AI-powered chatbot testing tool that focuses on ensuring quality, reliability, and safety in AI-based chatbots. The tool offers automated testing capabilities without the need for coding, making it easy for users to test their chatbots efficiently. With features like regression testing, performance testing, multi-language testing, and AI-powered coverage, bottest.ai provides a comprehensive solution for testing chatbots. Users can record tests, evaluate responses, and improve their chatbots based on analytics provided by the tool. The tool also supports enterprise readiness by allowing scalability, permissions management, and integration with existing workflows.

This repository provides an original implementation of Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications. It includes tools for neuron-level pruning, pruning based on set difference, Wanda/SNIP score dumping, rank-level pruning, and rank removal with orthogonal projection. Users can specify parameters like prune method, datasets, sparsity ratio, model, and save location to evaluate and modify neural networks for safety alignment.

NeMo Guardrails is an open-source toolkit for easily adding _programmable guardrails_ to LLM-based conversational applications. Guardrails (or "rails" for short) are specific ways of controlling the output of a large language model, such as not talking about politics, responding in a particular way to specific user requests, following a predefined dialog path, using a particular language style, extracting structured data, and more.

Inspect AI is a framework developed by the UK AI Safety Institute for evaluating large language models. It offers various built-in components for prompt engineering, tool usage, multi-turn dialog, and model graded evaluations. Users can extend Inspect by adding new elicitation and scoring techniques through additional Python packages. The tool aims to provide a comprehensive solution for assessing the performance and safety of language models.

This repository contains custom recipes for H2O Driverless AI, which is an Automatic Machine Learning platform for the Enterprise. Custom recipes are Python code snippets that can be uploaded into Driverless AI at runtime to automate feature engineering, model building, visualization, and interpretability. Users can gain control over the optimization choices made by Driverless AI by providing their own custom recipes. The repository includes recipes for various tasks such as data manipulation, data preprocessing, feature selection, data augmentation, model building, scoring, and more. Best practices for creating and using recipes are also provided, including security considerations, performance tips, and safety measures.

A curated list of Generative AI projects, tools, artworks, and models

Awesome AI Tools is a curated list of popular tools and resources for artificial intelligence enthusiasts. It includes a wide range of tools such as machine learning libraries, deep learning frameworks, data visualization tools, and natural language processing resources. Whether you are a beginner or an experienced AI practitioner, this repository aims to provide you with a comprehensive collection of tools to enhance your AI projects and research. Explore the list to discover new tools, stay updated with the latest advancements in AI technology, and find the right resources to support your AI endeavors.

The 100 Days in AI repository provides a comprehensive roadmap for individuals to learn Artificial Intelligence over a period of 100 days. It covers topics ranging from basic programming in Python to advanced concepts in AI, including machine learning, deep learning, and specialized AI topics. The repository includes daily tasks, resources, and exercises to ensure a structured learning experience. By following this roadmap, users can gain a solid understanding of AI and be prepared to work on real-world AI projects.

ModelBench is a tool for running safety benchmarks against AI models and generating detailed reports. It is part of the MLCommons project and is designed as a proof of concept to aggregate measures, relate them to specific harms, create benchmarks, and produce reports. The tool requires LlamaGuard for evaluating responses and a TogetherAI account for running benchmarks. Users can install ModelBench from GitHub or PyPI, run tests using Poetry, and create benchmarks by providing necessary API keys. The tool generates static HTML pages displaying benchmark scores and allows users to dump raw scores and manage cache for faster runs. ModelBench is aimed at enabling users to test their own models and create tests and benchmarks.

Awesome Generative AI & LLM APIs is a curated list of useful APIs that allow developers to integrate generative models into their applications without building the models from scratch. These APIs provide an interface for generating text, images, or other content, and include pre-trained language models for various tasks. The goal of this project is to create a hub for developers to create innovative applications, enhance user experiences, and drive progress in the AI field.

Reinforcement Learning from AI Feedback (RLAIF) is a concept that describes a type of machine learning approach where **an AI agent learns by receiving feedback or guidance from another AI system**. This concept is closely related to the field of Reinforcement Learning (RL), which is a type of machine learning where an agent learns to make a sequence of decisions in an environment to maximize a cumulative reward. In traditional RL, an agent interacts with an environment and receives feedback in the form of rewards or penalties based on the actions it takes. It learns to improve its decision-making over time to achieve its goals. In the context of Reinforcement Learning from AI Feedback, the AI agent still aims to learn optimal behavior through interactions, but **the feedback comes from another AI system rather than from the environment or human evaluators**. This can be **particularly useful in situations where it may be challenging to define clear reward functions or when it is more efficient to use another AI system to provide guidance**. The feedback from the AI system can take various forms, such as: - **Demonstrations** : The AI system provides demonstrations of desired behavior, and the learning agent tries to imitate these demonstrations. - **Comparison Data** : The AI system ranks or compares different actions taken by the learning agent, helping it to understand which actions are better or worse. - **Reward Shaping** : The AI system provides additional reward signals to guide the learning agent's behavior, supplementing the rewards from the environment. This approach is often used in scenarios where the RL agent needs to learn from **limited human or expert feedback or when the reward signal from the environment is sparse or unclear**. It can also be used to **accelerate the learning process and make RL more sample-efficient**. Reinforcement Learning from AI Feedback is an area of ongoing research and has applications in various domains, including robotics, autonomous vehicles, and game playing, among others.

FigStep is a black-box jailbreaking algorithm against large vision-language models (VLMs). It feeds harmful instructions through the image channel and uses benign text prompts to induce VLMs to output contents that violate common AI safety policies. The tool highlights the vulnerability of VLMs to jailbreaking attacks, emphasizing the need for safety alignments between visual and textual modalities.

The 'Awesome AI Guidelines' repository aims to simplify the ecosystem of guidelines, principles, codes of ethics, standards, and regulations around artificial intelligence. It provides a comprehensive collection of resources addressing ethical and societal challenges in AI systems, including high-level frameworks, principles, processes, checklists, interactive tools, industry standards initiatives, online courses, research, and industry newsletters, as well as regulations and policies from various countries. The repository serves as a valuable reference for individuals and teams designing, building, and operating AI systems to navigate the complex landscape of AI ethics and governance.

A curated list of open-ended learning AI resources focusing on algorithms that invent new and complex tasks endlessly, inspired by human advancements. The repository includes papers, safety considerations, surveys, perspectives, and blog posts related to open-ended AI research.

Welcome to our Awesome-llm-safety repository! We've curated a collection of the latest, most comprehensive, and most valuable resources on large language model safety (llm-safety). But we don't stop there; included are also relevant talks, tutorials, conferences, news, and articles. Our repository is constantly updated to ensure you have the most current information at your fingertips.

HybridAGI is the first Programmable LLM-based Autonomous Agent that lets you program its behavior using a **graph-based prompt programming** approach. This state-of-the-art feature allows the AGI to efficiently use any tool while controlling the long-term behavior of the agent. Become the _first Prompt Programmers in history_ ; be a part of the AI revolution one node at a time! **Disclaimer: We are currently in the process of upgrading the codebase to integrate DSPy**

AI-Security-and-Privacy-Events is a curated list of academic events focusing on AI security and privacy. It includes seminars, conferences, workshops, tutorials, special sessions, and covers various topics such as NLP & LLM Security, Privacy and Security in ML, Machine Learning Security, AI System with Confidential Computing, Adversarial Machine Learning, and more.

Awesome Responsible AI is a curated list of academic research, books, code of ethics, courses, data sets, frameworks, institutes, newsletters, principles, podcasts, reports, tools, regulations, and standards related to Responsible, Trustworthy, and Human-Centered AI. It covers various concepts such as Responsible AI, Trustworthy AI, Human-Centered AI, Responsible AI frameworks, AI Governance, and more. The repository provides a comprehensive collection of resources for individuals interested in ethical, transparent, and accountable AI development and deployment.

Awesome-LLM-Eval: a curated list of tools, benchmarks, demos, papers for Large Language Models (like ChatGPT, LLaMA, GLM, Baichuan, etc) Evaluation on Language capabilities, Knowledge, Reasoning, Fairness and Safety.

This repository is a collection of papers on Generative AI Machine Unlearning, categorized based on modality and applications. It includes datasets, benchmarks, and surveys related to unlearning scenarios in generative AI. The repository aims to provide a comprehensive overview of research in the field of machine unlearning for generative models.

Upload a site photo to assess the potential hazard and seek advises from experience AI Safety Officer

GPT used to classify prompts as valid inputs or injection attempts. Json output.

A specialized AI for optimizing traffic control, predicting bottlenecks, and improving road safety.

Advanced AI for chemistry, offering innovative solutions, process optimizations, and safety assessments, powered by OpenAI.

Ask questions, study together and prepare for exams.

Inspect and rate futuristic AI conceived VTOL aircraft.

構造体の写真を入力すると、弱点部位を分析してくれます

Advanced vehicle assessment tool with extensive capabilities.

A liaison GPT for AI safety emergencies, connecting users to OpenAI experts.

Summarises AI ethics papers, provides context, and offers further assistance.

AI Alignment guided by interdisciplinary wisdom and a future-focused vision.

A guide on QARRI's quantum-AI public safety innovations.

Expert on OSHA standards, ideal for safety professionals.

Informative assistant for safety and emergency training.

Identifies medications and active ingredients from photos for user safety.

Provides Construction Support relating to Planning Permission, Building Regulations, Party Wall Act and Fire Safety in the UK. Obtain instant Guidance for your Construction Project.

Friendly AI guardian with a crime trend analysis tool and holistic safety advice.

Your friendly AI assistant for voice-based dating, offering personalized tips, safety advice, and fun interactions.

Recall data on auto, consumer, and food product recalls

Generates risk maps, emergency response plans and safety protocols for disaster management professionals.