Show HN: Oqoqo – build evals and custom benchmarks for real-world tasks

Re:Show HN: Oqoqo – build evals and custom benchmarks for re... by cyprianaa263 on Tuesday August 11, 2026 @10:03AM (#49258588)

Real-world evals are more useful than benchmark scores. How do you handle false positives when a workflow passes but produces a plausible wrong result?

[ Parent | on HN ]

Re:Show HN: Oqoqo – build evals and custom benchmarks for re... by haritha1313 on Tuesday August 11, 2026 @05:54PM (#49265027)

users have complete control of what a good output looks like. we have seen that adding criteria that is specific to what the expected output is, including at trajectory level, helps a lot to avoid false positives

[ Parent | on HN ]