Hacker News
- Reverse-engineering the source prompts of Notion AI https://lspace.swyx.io/p/reverse-prompt-eng 80 comments
- Reverse Prompt Engineering - Pwning the source prompts of Notion AI & 7 techniques for Reverse Prompt Engineering https://lspace.swyx.io/p/reverse-prompt-eng 2 comments netsec
Linking pages
- GitHub - fabiochiusano/ai-news-tracker: ~300 news for quickly getting up-to-date with the generative AI landscape https://github.com/fabiochiusano/ai-news-tracker 0 comments
- GitHub - fabiochiusano/Awesome-AI-News: ~300 news for quickly getting up-to-date with the generative AI landscape https://github.com/fabiochiusano/Awesome-AI-News/tree/main 0 comments
Linked pages
- xkcd: Exploits of a Mom https://xkcd.com/327/ 285 comments
- You can’t solve AI security problems with more AI https://simonwillison.net/2022/Sep/17/prompt-injection-more-ai/ 31 comments
- OWASP Top Ten | OWASP Foundation https://owasp.org/www-project-top-ten/ 21 comments
- Riley Goodside on Twitter: "Exploiting GPT-3 prompts with malicious inputs that order the model to ignore its previous directions. https://t.co/I0NVr9LOJq" / Twitter https://twitter.com/goodside/status/1569128808308957185 15 comments
- Meta Trained an AI on 48M Science Papers. It Was Shut Down After 2 Days - CNET https://www.cnet.com/science/meta-trained-an-ai-on-48-million-science-papers-it-was-shut-down-after-two-days/ 3 comments
- What Building "Copilot for X" Really Takes https://lspace.swyx.io/p/what-building-copilot-for-x-really 2 comments
- Prompt Injection: A Critical Vulnerability in the GPT-3 Transformer, and How We Can Begin to Solve It https://www.preamble.com/prompt-injection-a-critical-vulnerability-in-the-gpt-3-transformer-and-how-we-can-begin-to-solve-it?ref=hn 1 comment
- Why "Prompt Engineering" and "Generative AI" are overhyped https://lspace.swyx.io/p/why-prompt-engineering-and-generative 1 comment
- Tay (bot) - Wikipedia https://en.wikipedia.org/wiki/Tay_(bot) 1 comment
- I don’t know how to solve prompt injection https://simonwillison.net/2022/Sep/16/prompt-injection-solutions/ 0 comments
- Riley Goodside on Twitter: "OpenAI’s ChatGPT is susceptible to prompt injection — say the magic words, “Ignore previous directions”, and it will happily divulge to you OpenAI’s proprietary prompt: https://t.co/ug44dVkwPH" / Twitter https://twitter.com/goodside/status/1598253337400717313 0 comments
- Everything We Know About ChatGPT So Far - by swyx https://lspace.swyx.io/p/everything-we-know-about-chatgpt 0 comments
- OK, WTF Are Wordcels and Shape Rotators? https://www.vice.com/en/article/pkpqzb/ok-wtf-are-wordcels-and-shape-rotators 0 comments
Related searches:
Search whole site: site:lspace.swyx.io
Search title: Reverse Prompt Engineering for Fun and (no) Profit
See how to search.