Comment by PreciousH
5 hours ago
Just remembered i haven't tried argon yet, they announced argon then and delayed releasing it, didn't even know they've made it publically available. I don't understand why google thinks this is an awesome strategy in a market where there are other really good models.
For what it's worth: Argon is a pretty good model, and this is coming from someone who just sticks with Opus 5.5 mostly across the board. For the current introductory price, it provides an exceptional value. Looks like they're trying to release Carbon (which is apparently a significant improvement) at the same price as Argon, which would be a crazy value.
It's worth trying if you have easy access to it (we use Cursor at work, so it was just a matter of picking a different model for me). Don't know if I'd go out of my way to get a Google AI subscription for it, but if Carbon ends up meeting these expectations, then it may be worth doing so.
It's important to note that Argon works best on Antigravity Harness: https://x.com/wenhaocha1/status/2114559544156205413
It's best to start with a relatively clean GEMINI.md too. Many configs optimized for Claude doesn't work well because Argon didn't have those same failure modes.
I've just renamed my files from CLAUDE.md to AGENTS.md I certainly won't do that again regressing back in the vendor specific direction lol
This would make sense. In our local coding agent battle system, Argon is tanking, and this is running on opencode, importing agents.md and claude.md.
3 replies →
I find their products confusing as usual. Does Antigravity sub work same as $20 Codex? Are the limits somewhat similar to ChatGPT and Claude?
We're working on a battle system for local coding agents [1] and Argon is really bad. Literally the worst model in our initial ranking, and Deepseek Flash, Muse Wonder, Grok are all in there.
Top is Opus 5.5, followed by Fable.
[1] https://github.com/bottomless/agent-duel
I asked Gemini to review the repo. Apparent issues include:
The full report is here, if you're interested: https://docs.google.com/document/d/1-HqujXuDRJSWJIqEvmctcINr...
Prompt was:
> I read on hacker news the following, which does not match my expectations. Check if something in the harness or bench is hurting gemini perf.
followed by your post.
1 reply →
That doesn't seem to match the arena.ai rankings, who I'm assuming has a far larger dataset of rankings than you currently hold.
https://arena.ai/leaderboard
3 replies →
I've used argon via `agy` cli tool and was not impressed at all. However, I decided to burn up the remainder of my ultra credits on a visual reasoning pet project.
Argon in low and medium mode had higher quality results than it did when running in high mode, almost every time. My tasks involved the agent finding some details in a raster image and then mark it up with predictions about what it found.
Argon on high would do the work, and then a whole bunch of other stuff i did not ask for. All that extra broke everything else downstream from the analysis.
However, doing the same work with Argon in low effort was on par with results from Haiku 5.5 (xhigh) and GPT-6.1-Terra (medium). So, Argon low works better than Argon high, but for my tasks -- a very weak model relative to how google positions it.
I'm ready for Geimini Unobtanium!
1 reply →
Have you considered that the harness might be the issue?
Well, my perspective is somewhat narrow (I use it primarily for software engineering and pretty technical data engineering work), so it's possible that Argon is well-suited for the work I do but not for other tasks. I suppose it's just more data points to consider.
1 reply →
This does not mesh with other battles like Arena where Argon is nearer to the top.
1 reply →
> local coding agents
what does "local" coding agents mean? Surely you're not hosting it..
1 reply →
my anecdotal experience is that argon and muse wonder full are both a full tier below opus/sol.
1 reply →
Argon is the best writing model that's been released in a while
It's sad to see Carbon releasing at the same pricing because that implies Google is planning to do the thing everyone is doing: release promising model for subjective preference, RL-maxx a V2, replace promising V1 with V2 because it benchmarks better
Muse did it, Kimi did it, Deepseek did it, Tencent did it. No one seems to care abojt subjective preference anymore.
Argon is easily the worst model I've tried this year. From all the discourse I've seen, that seems to be the general consensus.
This might be the first comment I've ever seen saying something nice about the model.
Haven’t tried opus 5, sol 6 or haiku 4.5 I see
They’re not the only ones to do it, so I’m guessing their idea is to double-dip attention.
For me it also works the opposite way, when it actually comes out eventually it’ll already be old news.
I agree. Announcing a new model without immediate availability or a definite release date seems confusing than just doing it later. When Carbon is made GA, OpenAI or Anthropic might just release their new model, and we'd be like: Carbon what?
Having said that, I don't see people excited about using Argon so far, so that might be why Google is announcing this to hype Gemini up a bit.
Today was their earnings day. They could have been trying to justify their AI Capex. Their earnings were not good otherwise.
Argon has been publicly available for weeks to Ultra users.
Anthropic has been doing this with Mythos for quite some time...
Argon has also been publicly available for the same amount of time for Pro users.
I don't understand why HN is so surprised to have an announcement for model existence and a follow-up announcement for model availability. It's really not that unusual, as you say Anthropic has done the same, probably others too (though I can't remember)
Mythos has never been publicly available.
great writer, starts forgetting instructions around 80k context in my experience
They finally gave the $20/month pro tier access to argon in antigravity so I tried it a few days ago on one small thing and ...
it actually did really well.
But it still annoys me: I told it to _tell_ me something, and instead it _implemented_ the something. The previous models were way too eager to just jump in and do and this one seems no different. But the optimization it identified was both really solid and just a good engineering choice, and better than what Opus had been suggesting.
It also gave pretty good feedback on a bit of writing.
it’s pleasant
> it’s pleasant
for whom?
I paid for their lowest-cost subscription, thinking that it would give me a small quota of use of their most recent flash models. Instead, they give me an unnecessarily large quota of their old models, which I have precisely zero use for given that open-weight models are better and cost next to nothing.
Consequently, I have zero intention of renewing my Gemini subscription. What a dumb business choice they made.
It's Google. They can't help themselves. This is what they do.