I beat all the popular harnesses on FrontierHarness Eval | Hacker News - But Better

I beat all the popular harnesses on FrontierHarness Eval github.com

An efficient AI coding agent extendable by neovim-like Lua plugins - tontinton/maki

4 points•tontinton•8 days ago•1 comment•

#frontierharness #harnesses #beat #popular #eval #frontierharness eval #popular harnesses #efficient

1 comment

scuppernong7 days ago

the charts on maki.sh and in the README don't seem to agree. what's the subtlety?

Read the full thread on Hacker News →

Related stories

Does this mean it's fine to use Claude subscriptions with third party harnesses?
Hacker News · 4 points · 13 days ago
Scaling Auto-Research Loops for Efficient Agent Harnessesnvlabs.github.io
Hacker News · 2 points · 6 days ago
Run-assert-eval: Find the risk, fix it, prove itcommandline.microsoft.com
Hacker News · 1 points · 6 days ago
7 Agent Eval Mistakes That Cost Me Weeks (And the One-Line Fixes That Ended Them)dev.to
DEV Community · 22 points · 7 days ago
Show HN: Griz`: a faster, more token efficient way to edit filestwitter.com
Hacker News · 1 points · 6 days ago
Maki, the efficient codermaki.sh
Hacker News · 2 points · 9 days ago