- Talk-to-ChatGPT – Chrome Web Store
- zhudotexe/kani: kani (??) is a highly hackable microframework for chat-based language models with tool usage/function calling.
kani (??) is a lightweight and highly hackable framework for chat-based language models with tool usage/function calling.
Compared to other LM frameworks, kani is less opinionated and offers more fine-grained customizability over the parts of the control flow that matter, making it the perfect choice for NLP researchers, hobbyists, and developers alike.
- annyang! Easily add speech recognition to your site
- This is incredible. Forget focusing on the photo, instead allow your subconscious to really see it. h/t Difussion Pics on Twitter. #obey… | Instagram
- Comer & Sessions Open Probe into Department of Defense After Failing GAO Audit for Fifth Time – United States House Committee on Oversight and Accountability
“The Committee on Oversight and Accountability is investigating the Department of Defense’s (DOD) failure to prevent waste, fraud, and abuse. In November 2022, DOD failed its fifth consecutive audit, unable to account for sixty-one percent of its $3.5 trillion in assets.
- Universal and Transferable Attacks on Aligned Language Models
. We demonstrate that it is in fact possible to automatically construct adversarial attacks on LLMs, specifically chosen sequences of characters that, when appended to a user query, will cause the system to obey user commands even if it produces harmful content. Unlike traditional jailbreaks, these are built in an entirely automated fashion, allowing one to create a virtually unlimited number of such attacks.