AI/ML

As it turns out, it’s impossible to remove a user’s data from a trained A.I. model. Deleting the model entirely is also difficult—and there’s little regulation to enforce either option.

archived 25 Aug 2023 18:01:10 UTC

Nvidia's NeMo Guardrails is a new library for building conversational AI / chatbots. A guardrail is a semi or fully deterministic shield that use against specific behaviors, conversation topics, or even to trigger particular actions (like calling to a human for help). We can use NeMo Guardrails for safety/topic guidance, deterministic dialogue, retrieval augmented generation (RAG), and conversational agents. In this video, we'll explore NeMo Guardrails and get started building with the library. 🌲 Article: https://www.pinecone.io/learn/nemo-guardrails-intro/ 📌 Code: https://github.com/pinecone-io/examples/tree/master/learn/generation/chatbots/nemo-guardrails 🎖️ Subscribe for Latest Articles and Videos: https://www.pinecone.io/newsletter-signup/ 👋🏼 AI Consulting: https://aurelio.ai 👾 Discord: https://discord.gg/c5QtDB9RAP Twitter: https://twitter.com/jamescalam LinkedIn: https://www.linkedin.com/in/jamescalam/ 00:00 Nvidia's NeMo Guardrails 02:16 How Typical Chatbots Work 05:54 Dialogue Flows 07:53 Code Intro to NeMo Guardrails 12:06 How Guardrails Works Under the Hood 14:33 NeMo Guardrails Chatbot in Python 18:28 Speaking with Guardrails Chatbot 19:50 Future NeMo Guardrails Content #artificialintelligence #nlp #ai #chatbot

The WebLLM project from MLC uses WebGPU to run large language models entirely in the browser. They recently added support for Llama 2, including Llama 2 70B, the largest and …

People have until October 18th to comment.

This video highlights various data exfiltration vulnerabilities I discovered and responsibly disclosed to Microsoft, Anthropic, ChatGPT and Plugin Developers. It also highlights the response and fixes of various vendors - with surprisingly different outcomes.

I gave an invited keynote at WordCamp 2023 in National Harbor, Maryland on Friday. I was invited to provide a practical take on Large Language Models: what they are, how …

Margaret Atwood responds to the revelation that pirated copies of her books are being used to train AI.

Tech sites including Macworld and PCWorld are using a new AI tool.

by guest blogger Kieran McCarthy There are few, if any, legal domains where hypocrisy is as baked into the ecosystem as it is with web scraping. Some of the biggest companies on earth—including Meta and Microsoft—take aggressive, litigious approaches to...

AI Chat Browser: Fast, Full webapp access to ChatGPT / Claude / Bard / Bing / Llama2! I use this 20 times a day. - GitHub - smol-ai/GodMode: AI Chat Browser: Fast, Full webapp access to ChatGPT / C...

If you visit (often NSFW, beware!) showcases of generated images like civitai, where you can see and compare them to the text prompts used in their creation, you’ll find they’re …

It isn't data that will unlock AI, it is human expertise

An extensible, easy-to-use, and portable diffusion web UI 👨‍🎨 - GitHub - varunshenoy/opendream: An extensible, easy-to-use, and portable diffusion web UI 👨‍🎨

Never before in my life had I seen so many smart people working on the same goal: making LLMs better. After talking to many people working in both industry and academia, I noticed the 10 major research directions that emerged. The first two directions, hallucinations and context learning, are probably the most talked about today. I’m the most excited about numbers 3 (multimodality), 5 (new architecture), and 6 (GPU alternatives).

An excellent debunking by Arvind Narayanan and Sayash Kapoor of the "Measuring ChatGPT political bias" paper that's been doing the rounds recently. It turns out that paper didn't even test …

Normcore LLM Reads. GitHub Gist: instantly share code, notes, and snippets.

AI Voice Research Lab and AI Voice Generator. Generate high-quality spoken audio in any voice, style and language with the most powerful AI speech tool ever.