Simon Willison’s Weblog

Twitter pranksters derail GPT-3 bot with newly discovered “prompt injection” hack. I’m quoted in this Ars Technica article about prompt injection and the Remoteli.io Twitter bot.

Posted 16th September 2022 at 6:33 pm

Recent articles

Introducing gisthost.github.io - 1st January 2026
2025: The year in LLMs - 31st December 2025
How Rob Pike got spammed with an AI slop "act of kindness" - 26th December 2025

security 571 twitter 160 gpt-3 67 openai 380 prompt-engineering 176 prompt-injection 139 generative-ai 1568 llms 1534 press-quotes 21

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