Pairing Perplexity with Microsoft Loop has reshaped the way I work. Perplexity handles the heavy lifting of surfacing clear, source-backed information, while Loop turns that information into something ...

RULER (Relative Universal LLM-Elicited Rewards) eliminates the need for hand-crafted reward functions by using an LLM-as-judge to automatically score agent trajectories. Simply define your task in the ...