Can you do better than our red teamers? We’ve made a demo system protected by Constitutional Classifiers. We challenge you to jailbreak it to help us make our defenses even stronger. Try the demo: http://
claude.ai/constitutional
-classifiers
…
PROMPT ENGINEERING
-
Constitutional Classifiers Demo: Security Challenge for AI Safety
By
–
-
Need New Terminology for AI Workflows Beyond Agents
By
–
Maybe we just need a new name for these AI-powered workflows. Something that also encompasses GPTs and other chatbots that are built around a single output. But not agents. Definitely not agents.
-
Critique de l’utilisation impropre du terme AI agents
By
–
just realized something really dumb I always took "AI agents" to be shorthand for "autonomous AI agents" Seems like there's a pretty large contingent that calls their prompts/prompt chains "agents" to make them sound cool Not a fan. "Agency" = Ability to act independently
-
Appending Wait to Model Generation as Path to AGI
By
–
« appending "Wait" multiple times to the model's generation » => current most likely path to AGI
-
Using ChatGPT to Replicate Business Strategies
By
–
Alex Hormozi’s $100M Offers is a goldmine for online businesses. I built a ChatGPT mega-prompt that replicates Hormozi’s mind. Get $100,000 worth of business insights for FREE! Like + comment "Alex" and I’ll DM you the link. (Must be following me to receive it)
-
Deep Research Feature Not Working: Troubleshooting Tips
By
–
I couldn't get Deep Research to work – the chats never went into any deep research mode. Any suggestions/tips?
-
Building an LLM Council with Debate and ELO-Based Chair Selection
By
–
This is cool! I want to build something like it too because I want my LLM council. First they all run, then they debate, and then the chair of the council (the highest ELO model) works out the final response.
-
Test AI Capabilities on Your Hardest Work Tasks
By
–
give it a try on your hardest work task that can be solved just by using the internet and see what happens.
-
Better prompts yield better results in AI systems
By
–
it can remain broad but you get better results with better prompts
-
AI Agents Automate Research Reports From Search Queries
By
–
If someone was using Google search for you and came back with a full research report from hours of searches