News for hackers. Stuff that matters.

A comment on Local Qwen isn't a worse Opus, it's a different tool. Parent comment

Re:Local Qwen isn't a worse Opus, it's a different tool by theshrike79 on Thursday June 18, 2026 @02:58PM (#48589859)
How would you benchmark "agent harness communicates with user clearly" it's 100% a feels measurement.
[ Parent | on HN ]
Re:Local Qwen isn't a worse Opus, it's a different tool by sanderjd on Thursday June 18, 2026 @08:59PM (#48593685)
I mean, in my experience some of this stuff is way closer to table stakes things than that. Like "the tool call didn't get totally confused" more than "did the communication with the user feel good".
[ Parent | on HN ]