Sapien (@BuildOnSapien): Microsoft Research published notes on its May research around AI delegation and long-horizon reliability. The benchmark studies delegated workflows wh…
Estimated coin impact
Scores are not price-change percentages. High impact means a score of +70 or more, or -70 or less.
Impact unavailable
Microsoft Research published notes on its May research around AI delegation and long-horizon reliability. The benchmark studies delegated workflows where an AI modifies important artifacts over multiple steps. Frontier models introduced sparse but consequential errors, with