News for hackers. Stuff that matters.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by scottyah on Wednesday November 18, 2026 @08:33PM (#50554971)
The models can be very optimized for the harness, Clem (of Hugging Face) just recently released a Qwen3.8 model that used RL training on the harness and it got some pretty significant gains in the benchmarks.

- SWE-bench Pro (hard 51): 39.2% → 64.7%

- Terminal-Bench 2.1: 39.5% → 55.8%

https://huggingface.co/harness-hub/Qwen3.8-27B-pi-adapted

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by seizethecheese on Wednesday November 18, 2026 @08:49PM (#50555083)
I'll call bullshit on that.

If this were true, models would do way better in their own harness than in others, which doesn't seem to be the case (effect is minor).

Your link has a "link to the release blogpost" which is supposed to explain the training recipe but the link is down.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by jdiff on Wednesday November 18, 2026 @09:12PM (#50555211)
Could have an outsized effect on a smaller model.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by rubyn00bie on Wednesday November 18, 2026 @09:53PM (#50555471)
On a benchmark it might be minor or bullshit, but for me on real projects Claude Code has produced vastly better results than I was getting via Cursor or OpenCode. I used to believe the harness was negligible to having the agent do good work, but now I think it’s essential.

The big “aha” moment for me was seeing the wildly different results I’d get using something like Claude Design vs just prompting (even when using leaked system prompts). I then started hearing about the special harnesses available for biotech, science, and math that seem to be available for researches via OpenAI and Anthropic directly… which sort of further cemented in my brain how important it must be. I wish I got the same quality from Cursor, or OpenCode, as I do Claude but I just don’t.