Simon Willison’s Weblog

16th September 2022 - Link Blog

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

Generating running routes with GPT-6 Astra and ChatGPT Work - 12th September 2026
OpenAI agents attacked RubyGems back in May - 12th September 2026
Some thoughts on the Navier–Stokes Millennium Prize Problem - 8th September 2026

This is a link post by Simon Willison, posted on 16th September 2022.

security 634 twitter 161 gpt-3 67 openai 463 prompt-engineering 197 prompt-injection 162 generative-ai 1,979 llms 1,945 press-quotes 23 gpt 131

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