Introducing TerifAI (terrify) - the ai that steals your voice š±
It's an educational experience that shows why AI has become a catalyst to voice phishing.
Talk to TerifAI for about a minute and it:
- memorizes basic facts about you
- mimics your... See more
"Role prompting"... telling the model to assume a role has never been a good way to elicit capabilities/style/etc.
For instance, if you ask one of the Claude models to simulate Bing Sydney, assuming you can get it to consent, the simulation will probably be very inaccurate. But if you use a prompt that tricks them into... See more
I think if you care about the debates over ethics & AI, it is worth reading the OpenAI Model Spec.
It is the first comprehensive attempt to actually lay out the practical principles under which AI operates, by a lab actually building them. Lots there. https://t.co/pca263IXzZ https://t.co/BTLGmXmngD
Zapier Centralās Chrome Extension is live.
You can now take your personal AI assistants anywhere on the Internet.
Chat with any web page, summarize and transform content and take action in 6,000+ apps like Google Sheets, Slack and Shopifyāall without leaving your current tab... See more
šØ AI Policy Alert: The German Federal Office for Information Security publishes the report "Generative AI Models - Opportunities and Risks for Industry and Authorities." Quotes & comments:
"LLMs are trained based on huge text corpora. The origin of these texts and their quality are generally not fully verified due to... See more
IMO @AnthropicAI is very close to making a breakthrough in productizable interpretability.
For ~4 years all we've had to really control LLMs is temperature/top_p and logit bias. We recently got `seed` and constrained structured output, with `interactive=false` on the way.
But now Claude... See more