On this day: Feb 9

Demonstrated the limits of people polishing prompts by hand. Empirical grounds for the narrative that prompt engineering is in decline

The first empirical evidence that debate-based oversight actually raises the accuracy of non-expert judges

Publicly demonstrated that in a live service the system prompt does not work as a line of defense

Learns on its own, through self-supervised learning, when to call APIs and with what arguments — the route of building tool use into the weights