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

JustHTML is a fascinating example of vibe engineering in action - 14th December 2025
OpenAI are quietly adopting skills, now available in ChatGPT and Codex CLI - 12th December 2025
GPT-5.2 - 11th December 2025

security 569 twitter 160 gpt-3 67 openai 374 prompt-engineering 175 prompt-injection 138 generative-ai 1531 llms 1497 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