Simon Willison’s Weblog

18th August 2023 - Link Blog

Compromising LLMs: The Advent of AI Malware. The big Black Hat 2023 Prompt Injection talk, by Kai Greshake and team. The linked Whitepaper, Not what you’ve signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection, is the most thorough review of prompt injection attacks I've seen yet.

Posted 18th August 2023 at 2:46 am

Recent articles

DeepSeek V4 - almost on the frontier, a fraction of the price - 24th April 2026
Extract PDF text in your browser with LiteParse for the web - 23rd April 2026
A pelican for GPT-5.5 via the semi-official Codex backdoor API - 23rd April 2026

This is a link post by Simon Willison, posted on 18th August 2023.

security 598 ai 1985 prompt-injection 147 llms 1727

Monthly briefing

Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.

Pay me to send you less!

Sponsor & subscribe