New ASCII art attacks can jailbreak LLMs

Written By Luka Anicin

New ASCII art attacks can jailbreak LLMs. Anthropic releases new AI models, Elon Musk sues OpenAI, and Google is taking steps to tackle AI spam content.

What a week of events in the AI space, let's dive into them.

📰 News:

ℹī¸ ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs

🔗 https://lnkd.in/dGKu3_cD

ℹī¸ Anthropic presents the Claude 3 family. Three new large language models with impressive benchmarks.

🔗 https://lnkd.in/d8dTSPXj

ℹī¸ Here Comes The AI Worm: Unleashing Zero-click Worms

🔗 https://lnkd.in/dmqn7QNZ

ℹī¸ New ways of tackling spammy, low-quality content on Search | Google

🔗 https://lnkd.in/dC4YpYyq

ℹī¸ Elon Musk sues OpenAI for abandoning original mission for profit

🔗 https://lnkd.in/dEFzbvnK

ℹī¸ Adobe previews new generative AI tools for crafting and editing custom audio

🔗 https://lnkd.in/dtheGc99

Luka Anicin
Previous

The European Union đŸ‡ĒđŸ‡ē is the first to adopt regulations with the AI Act
Next

Singapore sends people 40+ back to school to prepare them for the age of AI