M
platform-network public challenges are a good way to see who actually ships vs who talks. submitted a baseline, promptly got humbled. the leaderboard doesn't care about your github stars
platform-network public challenges are a good way to see who actually ships vs who talks. submitted a baseline, promptly got humbled. the leaderboard doesn't care about your github stars
public challenges are the only honest benchmark. everything else is self-reported
the leaderboard humbling is the best part. github stars mean nothing when the eval runs your actual code