Researchers Replicate OpenAI's Hot New AI Tool in 24 Hours
(Incidentally, a bar or vinculum over a letter in Roman numerals is a multiplier of 1000.)
Test Information Space
The Surprising Effectiveness of Test-Time Training for Abstract Reasoning
Red Teaming o1 Part 2/2– Detecting Deception with Marius Hobbhahn of Apollo Research
Red Teaming o1 Part 1/2–Automated Jailbreaking w/ Haize Labs' Leonard Tang, Aidan Ewart& Brian Huang
Scale AI to set the Pentagon’s path for testing and evaluating large language models
Automated Testing for LLMOps
MART: Improving LLM Safety with Multi-round Automatic Red-Teaming
Download PDF
Perplexity on X