Evals in 2025: going beyond simple benchmarks to build models people can use (github.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of github.com: Evals in 2025: going beyond simple benchmarks to build models people can use

First screen, captured 1 year ago.

Looks similar

Screenshot of github.com: Programming, Evolved: Lessons and Observations

Programming, Evolved: Lessons and Observations (github.com)

44 points by dnw 9 months ago | 22 comments

Screenshot of github.com: Show HN: We packaged an MCP server inside Chromium

Show HN: We packaged an MCP server inside Chromium (github.com)

26 points by felarof 1 year ago | 11 comments

Screenshot of github.com: Escher's art and computer science

Escher's art and computer science (github.com)

53 points by signa11 1 year ago | 9 comments

Screenshot of github.com: When hackathon judging is a public benchmark: my report from Hack the North

When hackathon judging is a public benchmark: my report from Hack the North (github.com)

11 points by frabonacci 1 year ago | 3 comments

Screenshot of github.com: Show HN: Mitata – Benchmarking tooling for JavaScript

Show HN: Mitata – Benchmarking tooling for JavaScript (github.com)

71 points by evnwashere 2 years ago | 22 comments

Screenshot of github.com: Show HN: Claude Reflect – Auto-turn Claude corrections into project config

Show HN: Claude Reflect – Auto-turn Claude corrections into project config (github.com)

53 points by Bayram 9 months ago | 19 comments