Last Friday I had a shower thought about evals. An eval is a repeatable experiment on an LLM system: fixed inputs, one or more variants under test, and a scoring rule that turns outputs into number…

ALT: Waiting

I won't bury the lede, I'm looking to go back to work full-time. I'm thankful to not be under financial strain, so I'm not rushing into anything. Instead I'm coming at this from a place of genuine int...

Parag Agrawal says AI agents are the target customers for his new startup, Parallel.

Source

The reviews are finally in for Apple TV's latest sci-fi series.

Take a peek inside.

OpenAI is building its own X-like social media network, according to a new report from The Verge. The project is still in the early stages, but there's an

A helicopter crashed Thursday into the Hudson River off Manhattan, authorities said. The fire department said it received a report of a helicopter in the water near at 3:17 p.m.