frankie
@FrankieIsLost
this is a really great test for AI tool proficiency, since it requires working with long-running tasks, multi-step reasoning, tool use and iterative debugging.
here's a leaderboard for it if you want to enter the arena:
here's a leaderboard for it if you want to enter the arena:
Anthropic@AnthropicAI · Jan 22New on the Anthropic Engineering Blog: We give prospective performance engineering candidates a notoriously difficult take-home exam. It worked well—until Opus 4.5 beat it.
Here's how we designed (and redesigned) it: anthropic.com/engineering/AI…
Open quoted post →Here's how we designed (and redesigned) it: anthropic.com/engineering/AI…
12 168