News for hackers. Stuff that matters.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by seizethecheese on Wednesday November 18, 2026 @08:21PM (#50554850)
Totally possible for your use case, though the analyses I’ve done on harness model interactions show it’s actually not that important for benchmark performance. https://micjm.com/blog/on-model-harness-interactions/

For what it’s worth, the linked article data (Agent Duel data) is all run on OpenCode. I’m curious if people would prefer we run each model in its native harness (at the expense of user experience because it’ll be buggy).

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by thanhhaimai on Wednesday November 18, 2026 @09:40PM (#50555387)
Harness plays a significant part in benchmarking performance.

Here is an example from FrontierCS bench: https://x.com/wenhaocha1/status/2114559544156205413

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by seizethecheese on Wednesday November 18, 2026 @10:31PM (#50555732)
We can trade posts because I did my own analysis and found almost no effect https://micjm.com/blog/on-model-harness-interactions/