blake-raymond
Re:We Tested Coding Agent Harnesses. Thinking Harder Beat All of Them
on Thursday November 05, 2026 @11:15AM (#50380963)
They used their own proprietary benchmark called sudo L7, which purports to evaluate staff-level engineering judgment more than the correctness of the code itself.
Not surprising to me that higher thinking will outperform coding harnesses here.
Re:Ask HN: Why is it so hard to promote/market even when the product s...
on Wednesday November 04, 2026 @11:34AM (#50368040)
There is no conundrum.
Your potential customers want you to succeed. Everyone has problems, and people are rational. If you actually solve a real problem people have, find those people, effectively communicate your solution to them, and charge something they can afford, they will pay for it.
Any failed project is missing one or more of those.