All Stories

December 2023

• LLMs for Evaluating LLMs

  A good watch on LLMs as Evaluators

  December 10, 2023

• Karpathy on Hallucinations

  Dream machines: it's a feature, not a bug

  December 10, 2023

• LLMonitor Benchmarks

  Weekly benchmarks of popular LLMs using real-world prompts

  December 10, 2023

• Adversarial dataset creation challenge for text-to-image generators

  Novel and long tail failure modes of text-to-image models

  December 10, 2023

• Frontier Group launches for AI Safety

  The Big Guns get safer together

  December 10, 2023

• AI Engineer Summit

  Recordings now on YouTube

  December 10, 2023

April 2023

• How To Avoid Leaking PII to ChatGPT

  A proof-of-concept JavaScript tool to prevent IP address leakage in ChatGPT interactions.

  April 22, 2023

• ChatGPT bug bounty program doesn’t cover AI security

  AI Security: The Limits of Bug Bounty Programs and the Need for Non-ML Red Teaming

  April 15, 2023

• Defending Against Deepfakes

  Have you agreed on a safe word with your loved ones yet?

  April 15, 2023

• Chat Markup Language (ChatML)

  Establishing Conversational Roles and Addressing Syntax-Level Prompt Injections

  April 15, 2023

Page 4 of 11