Hacker News
Gemini 4 Neon looks like an Opus 5.5 competitor
theturtletalks
|next
[-]
We’re reaching the point where certain models are really good at 1 thing. The person writing this blog post isn’t using Neon for large-scale orchestration, but I’m sure it excels in its usage. For me Fable 5.2 as the orchestrator and Opus 5.5 and grunt workers have led to the most robust software...so far.
wmf
|next
|previous
[-]
seizethecheese
|root
|parent
[-]
The blog itself can be seen more as an exploration of how speed impacts coding agent battle votes, than anything specifically about Neon.
Applying the speed impact to Gemini Carbon is particularly interesting, though, because it's the top model in our leaderboard when you exclude early votes (https://agentduel.com/leaderboard?excludeEarlyVotes=true) but mediocre when you let developers vote. Gemini literally takes 3x as long as opponents in matched battles.
bwat49
|next
|previous
[-]
rootusrootus
|next
|previous
[-]
But that's about as complicated as I get. I have recently tried to use Copilot because that is what work wants us to use, and even with Opus 5.5 it is noticeably inferior to CC on the same model. Wild. So clearly the harness matters.
scottyah
|root
|parent
|next
[-]
- SWE-bench Pro (hard 51): 39.2% → 64.7%
- Terminal-Bench 2.1: 39.5% → 55.8%
seizethecheese
|root
|parent
[-]
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.
seizethecheese
|root
|parent
|next
|previous
[-]
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).
anukin
|root
|parent
|next
|previous
[-]
thefunnyman
|root
|parent
|next
|previous
[-]
rootusrootus
|root
|parent
[-]
My company is slow-walking (and that is an understatement) our LLM usage, so the majority of work that I'm reviewing is human generated. After the stories I hear of what other people are experiencing when management is more enthusiastic, maybe I should count myself lucky.
TacticalCoder
|root
|parent
|next
|previous
[-]
"OK, google models perform just as well, are faster and are cheaper but all that doesn't matter. Because the models, now that Google has very good ones, doesn't matter after all. All that matters is the harness".
And of course it's upvoted by the Anthropic shills.
quinndupont
|next
|previous
[-]
seizethecheese
|root
|parent
|next
[-]
afavour
|next
|previous
[-]
For this model, I mean. And not the Anthropic IPO.
lacoolj
|next
|previous
[-]
Second, I will be trying this with agy when my Opus 5.5 limit hits. I only hope its faster than Argon which is already dog slow
ralusek
|next
|previous
[-]
"It looks like he's dead."
"...He's covered in blue paint, or something."