News for hackers. Stuff that matters.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by afavour on Wednesday November 18, 2026 @08:05PM (#50554692)
Looks like a good bunch of speculation in there no bad news to be found. Just as good but cheaper? Sign me up.

For this model, I mean. And not the Anthropic IPO.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by seizethecheese on Wednesday November 18, 2026 @08:08PM (#50554729)
[delayed]
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by enraged_camel on Wednesday November 18, 2026 @08:37PM (#50554997)
Nobody with money is gonna look at this model and change their opinion on the Anthropic IPO lol
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by quinndupont on Wednesday November 18, 2026 @08:09PM (#50554735)
Fun analysis. I guess it’s not surprising to see the need for speed™ as an important factor, but who is using Fable for run of the mill coding work? It’s too pricey!
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by seizethecheese on Wednesday November 18, 2026 @08:16PM (#50554795)
Yeah, check out DeepSeek performance on the leaderboard. It wins ~half the time because it’s lightning fast and good enough.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by Rodmine on Wednesday November 18, 2026 @11:33PM (#50556117)
Finally, something that has actually reflected my real experience with these models.

All the rest I have seen are victims of benchmaxxing and therefore simply misleading.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by seizethecheese on Thursday November 19, 2026 @12:14AM (#50556320)
Really happy to hear this. We're trying to build a leaderboard that reflects real work done by real people. Even the Arena systems are run in cloud containers.

Genuinely hoping some people sign up from this and use the app so we can get some more high quality data (it's open source: https://github.com/bottomless/agent-duel).

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by hedgehog on Wednesday November 18, 2026 @08:24PM (#50554887)
I used it to write something last night that was intricate enough that Opus would have involved a lot more rework. Subscription discount though.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by elxr on Wednesday November 18, 2026 @11:07PM (#50555971)
When you're making >$240K a year, I imagine spending $80-90 a day trying all the models just to find a slight edge is barely noticeable.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by rootusrootus on Wednesday November 18, 2026 @08:15PM (#50554778)
I guess what I really want to know is how Gemini 4 Neon w/Antigravity compares with Opus 5.5/Claude Code. I'm not really into using LLMs in a particularly advanced way, I just use CC like 99% of the time when I need to write something, and then maybe Codex to second guess it.

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.

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/
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by thefunnyman on Wednesday November 18, 2026 @08:23PM (#50554870)
We had CC for a while and now have to use GHCP. As such I haven't used CC in like 6 months but around the time I switched I felt like GHCP CLI had pretty much caught up. Curious to hear what you feel are the gaps? Are you using the cli versions of both?
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by rootusrootus on Wednesday November 18, 2026 @08:56PM (#50555124)
Yep, CLI versions for both GHCP and CC. To be honest, I haven't done enough actual coding with GHCP yet to get a feel, so my original comment may be too broad. But I've been repeatedly comparing and contrasting with CC for code reviews (as a team lead, I do more of that these days than coding). I have been pretty consistently getting about half again as many bugs from CC as from GHCP. And very nearly always correct, not hallucinations.

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.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by pritambarhate on Wednesday November 18, 2026 @08:26PM (#50554903)
Also last I checked there was no clear flag to turn off training in paid plan of Antigravity. So if you care about that looks like Google doesn’t want you as their customer.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by riskassessment on Thursday November 19, 2026 @12:20AM (#50556359)
I think you just turn off telemetry in antigravity to disable training. The Gemini app (including the web chatbot) is much more frustrating: the only way to disable training in the Gemini app (for a personal account) is to turn off apps and history.
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.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by anukin on Wednesday November 18, 2026 @08:44PM (#50555048)
Antigravity in general is a poor harness. I have had better experience using Gemini 3.8 flash over api than using it over agy.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by TacticalCoder on Wednesday November 18, 2026 @09:01PM (#50555157)
Ah that's a new angle. After the "Google models are behind" and the "Google models are slower" and the "Google costs more per tokens", we're now at the following phase:

"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.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by ddxv on Wednesday November 18, 2026 @09:42PM (#50555416)
A lot of this is brand affiliation as well.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by vrosas on Wednesday November 18, 2026 @10:20PM (#50555645)
Don't forget "I couldn't figure out how to buy a subscription" and "The names are confusing"
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by rootusrootus on Wednesday November 18, 2026 @11:21PM (#50556055)
That's what you got from what I wrote?

I must not be deep enough into the conversation to get it. I was just sharing my own perspective. I don't follow AI development nearly as close as a lot of HN does. I don't hate it, but I don't love it either, it's just part of my job now.

> And of course it's upvoted by the Anthropic shills.

Gotta tell you, my post is barely above water ;-). It goes up, goes right back down, plenty of people seem to agree with you that I'm being mean to Google or something.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by retsibsi on Thursday November 19, 2026 @12:35AM (#50556429)
> "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".

Have they edited their comment since you replied? If not, this is one of the most egregious strawmen I've seen this week. You have brought a lot of your own baggage to this discussion, and stuffed it into a comment that said approximately none of what you claim to have taken from it.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by TiredOfLife on Thursday November 19, 2026 @12:27AM (#50556388)
It's really simple. You somehow trigger an account ban for Claude you lose that account and create another one.

You get the same with antigravity and you get your whole Google account banned

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by bwat49 on Wednesday November 18, 2026 @08:26PM (#50554904)
I'm pretty impressed so far, this is the first google model I've used that feels good for coding
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by tcoff91 on Wednesday November 18, 2026 @08:56PM (#50555129)
Is it still dog slow like other gemini models?
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by nicce on Wednesday November 18, 2026 @09:07PM (#50555190)
Gemini Flash is one of the fastest?
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by seizethecheese on Wednesday November 18, 2026 @09:22PM (#50555278)
the speed is in TFA too
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by semireg on Wednesday November 18, 2026 @10:04PM (#50555535)
127 tps
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by elxr on Wednesday November 18, 2026 @10:51PM (#50555860)
What harness? And how much do they subsidize compared to the equivalent chatGPT sub?
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by wmf on Wednesday November 18, 2026 @08:32PM (#50554953)
Projecting something that is already out is an epistemic crime.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by seizethecheese on Wednesday November 18, 2026 @08:44PM (#50555039)
[delayed]
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by NBJack on Wednesday November 18, 2026 @10:04PM (#50555536)
Why not just...post later when you have data?
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by seizethecheese on Wednesday November 18, 2026 @10:19PM (#50555632)
[delayed]
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by outside1234 on Wednesday November 18, 2026 @10:20PM (#50555636)
Engagement

To be fair, I don't have the model either but after reading this I will give it a try since Opus 5.5 is my go-to right now.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by seizethecheese on Wednesday November 18, 2026 @10:52PM (#50555868)
It was an excuse to write about the impact of speed on battle votes, and I got lucky that people wanted to talk about Neon.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by wasabi991011 on Thursday November 19, 2026 @12:14AM (#50556322)
What makes something an "early vote" and a "developer vote", as opposed to just a "vote"? And what makes those categories meaningful to agent duel?

(Also, out of curiosity, how are you funding this free inference for frontier models Is this not massively abuseable?)

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by seizethecheese on Thursday November 19, 2026 @12:35AM (#50556425)
> What makes something an "early vote"

In the battle, if side A finishes before side B we allow the user to vote for A before B finishes. (This is contrary to Arena.ai methodology, but I think it's the right thing for agents when sides can take a dramatically different amount of time.) This is why DeepSeek 4.1 Flash is doing so well in our leaderboard, it's super fast and often sufficient.

> and a "developer vote"

This is confusing, sorry. Inspecting our data it's almost entirely people doing software developments with agents. It's just a vote.

> (Also, out of curiosity, how are you funding this free inference for frontier models Is this not massively abuseable?)

This is a pivot from Bottomless (YC W19). That business is doing okay and funding our runway, in addition to fundraising back in 2021.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by lacoolj on Wednesday November 18, 2026 @08:42PM (#50555028)
First, this post has a lot of words like "assume" and "projected". What are we actually reading here?

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

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by fud101 on Wednesday November 18, 2026 @08:50PM (#50555088)
I'm blown away by Neon, it's as good as Argon (which was amazing) but fast and cheap (i think). Opus is trash, Fable is trash - I will just use Opus for Day Job which it handles with ease and keep Neon for my serious side projects which Claude can't handle well at all.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by ralusek on Wednesday November 18, 2026 @08:51PM (#50555092)
This title reminds me of the doctor from Arrested Development.

"It looks like he's dead."

"...He's covered in blue paint, or something."

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by theturtletalks on Wednesday November 18, 2026 @09:01PM (#50555163)
I’ll give it a spin on my software factory. The other Gemini models looked good initially and in benchmarks, but on long-running sessions and orchestration, it’s fallen short.

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.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by seizethecheese on Wednesday November 18, 2026 @09:08PM (#50555197)
> The person writing this blog post isn’t using Neon for large-scale orchestration, but I’m sure it excels in its usage

I'm the person writing this. This is head to head battle data by real developers on top of OpenCode. The data is generated by an open source app so you can inspect it yourself (https://github.com/bottomless/agent-duel). The hitch is there's no real Neon data. This is purely projecting from Carbon's super slow but very good performance onto Neon's likely fast and likely equal performance.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by getcrunk on Wednesday November 18, 2026 @09:49PM (#50555450)
Software factory?
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by klodolph on Wednesday November 18, 2026 @09:52PM (#50555463)
Multi-agent coding orchestration setup.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by rogerrogerr on Wednesday November 18, 2026 @10:22PM (#50555669)
Token incineration plant.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by esseph on Wednesday November 18, 2026 @10:24PM (#50555681)
[delayed]
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by Implicated on Wednesday November 18, 2026 @10:47PM (#50555841)
Dear god, as someone who has built a wildly robust "software factory" (mine doesn't stop at the output) - don't fork sessions. Just don't. Distill the relevant context into a new session, however you choose to do that.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by kaydub on Wednesday November 18, 2026 @10:26PM (#50555702)
Rube goldberg machine where tokens are burnt and code is sorta-kinda created.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by SimianSci on Wednesday November 18, 2026 @11:02PM (#50555938)
An impressive showcase of productivity theatre in which tokens are incinerated in exchange for software that is always never "finished" and will continuously let down its users.

Some people have cleverly parlayed this new fad into money, but this is typically a result of their sales techniques rather than their software.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by nonethewiser on Wednesday November 18, 2026 @11:20PM (#50556045)
I havent tried it but this was my take as well. Forget token inefficiency, it just seems much harder than just prompting a single agent what you want
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by reassess_blind on Wednesday November 18, 2026 @11:29PM (#50556095)
Replace “tokens” with “man hours” and it sounds like a software company.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by UltraSane on Wednesday November 18, 2026 @11:32PM (#50556112)
Gas Town and Gas City are textbook examples.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by xtracto on Wednesday November 18, 2026 @11:56PM (#50556218)
Just tried this today. Installed gascity, set it up with "gastown" settings, added a couple of repos and pointed it to a [bot to crazy] jira ticket .

It just make things so complicated... and in the end I had to chat with the "major" interactively, and I didn't see any benefit vs a simple claude session + a "work with 10 agents" prompt. It just seemed complicated for the sake of it.

I want a system that hides the complexity, and is effectiveand efficient. But we're still not there.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by mrheosuper on Wednesday November 18, 2026 @11:29PM (#50556096)
Industrial space heater.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by reilly3000 on Wednesday November 18, 2026 @11:48PM (#50556184)
Planet-scale really.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by pkulak on Thursday November 19, 2026 @12:07AM (#50556276)
I never use long running sessions. I like one small task at a time that I can understand and evaluate. If the only downside is worse one-shot GTA homages, that’s a pretty good trade off.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by jdw64 on Wednesday November 18, 2026 @09:14PM (#50555223)
I’m considering AntiGravity because its subscription usage seems lower than expected. But personally, with Gemini’s Carbon, Hydrogen, and Neon, it’s confusing because they don’t show which model is mid-to-low-end and which is flagship. OpenAI’s model names—Astra, Sol, Terra, Luna are intuitive, like cosmos–sun–earth–moon. Google’s model names aren’t intuitive. If we go by abundance, Hydrogen should be the top model.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by itemize123 on Wednesday November 18, 2026 @09:48PM (#50555447)
looking at the cost - Hydrogen, Neon, Argon ~ Carbon. intuitively they are by 'weight' of the elements atoms
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by naniwaduni on Wednesday November 18, 2026 @10:33PM (#50555752)
"Argon ~ Carbon" is a bit of a "have you looked at a periodic table recently?"
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by ijidak on Thursday November 19, 2026 @12:03AM (#50556258)
It's wild that Google can fumble something as basic as heirarchical naming.

I have no idea whether argon, carbon, or neon is their largest/best model.

If they think we're going to pull out a periodic table to understand the naming scheme, they shouldn't be in charge of product.

All of the providers have chosen a somewhat nerdy naming scheme, but that's fine given the current mostly tech customer base, but at least Anthropic's and OpenAI's are intuitive.

But, the order of elements in the periodic table is not something most people have memorized unless you do something like hydrogen, helium, lithium, maybe.

Or maybe iron, copper, silver, gold.

Maybe at least pick elements that are in horizontal order, like carbon, nitrogen, oxygen.

Just so many basic mistakes in every aspect of product rollout at Google.

Re:Gemini 4 Neon looks like an Opus 5.5 competitor by jdw64 on Thursday November 19, 2026 @12:21AM (#50556361)
I hit the upvote button.. These days Google seems focused on B2B and not interested in B2C. Honestly, it’s too non-intuitive. Before even memorizing the periodic table, it feels a bit ambiguous. It’s not even that they get bigger in order of atomic number.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by byzantinegene on Wednesday November 18, 2026 @11:32PM (#50556105)
the timing of this release almost feels like a stab toward anthropic. which is weird because google owns 13% of anthropic
Re:Gemini 4 Neon looks like an Opus 5.5 competitor by lofaszvanitt on Thursday November 19, 2026 @12:33AM (#50556415)
Oh it's ugly. That's their way of showing how they love each other ;).