What I don't understand is how they all make it work with caching in general. Looking at how the advisor mode in claude work you seem to only be billed the output tokens and cache hit on the whole session when it calls out to the advisor, making it super cheap compared to running the more expensive model for the entire session.
Gemini 4 Hydrogen and Orchestrator (antigravity.google)
vegardx 4 hours ago
lemonish97 4 hours ago
jeremyjjj 3 hours ago
Orchestrator seems to automatically delegate things to subagents as required is my read of it. This should be fine for caching.
artdigital 2 hours ago
But a new Flash model is very welcome. Argon and Carbon are very slow. In the time it takes for them to complete a single task, Opus already managed to complete multiple things. They’re so slow, I started using 3.8 Flash over them. (A lot of it is also because of how terrible agy is. Before doing any task, Gemini feels the need to hover up a bazillion files into its context when the task is something simple like “update the docs of this controller”)
Also this sounds like Argon is dead now
fmind-dev 5 hours ago
fuussssip 5 hours ago
I set up my subagents with specific models based on how complex I believe the problem space is. I'm nervous to delegate that authority to a model (since models tend to be... optimistic about their capabilities.)
That said, not every coding task is a difficult coding task. Plenty are boilerplate, plumbing, or simple test authoring that could use a flash model, so maybe this would downgrade nicely.
On the other hand, it's trivial for me to set up some guidelines to create different subagents for different task domains, and just pin those models to those tasks -- implementor (hard) and implementor (easy) or whatever.
pietz 4 hours ago
I’m glad Google is kinda back, but today there’s no reason to code with Gemini.
vrosas 4 hours ago
imafish 4 hours ago
engineer_22 3 hours ago
pietz 3 hours ago
Carbon is the first "better than meh" model form Google in more than half a year. It's been out for less than a week. How can you consider it "steady"? Their subscription and even the API has been terribly unstable throughout the past few days, so I'm having really trouble believing any of this.
vrosas 2 hours ago
ilteris 2 hours ago
pietz 2 hours ago
Ok, you're either a troll or you objectively don't know what you're talking about. Google should be ashamed they even released 3.8 Flash. They published models with such high frequency and always made a huge jump on benchmarks. Then they were caught, when a new version of AA came out and their numbers dropped like a stone.
baoooooooooooo 2 hours ago
My partner runs an internal computational mechanics benchmark that hasn’t tracked progress with model advancements (flat/no progress since early 2026) until suddenly saturating from argon and carbon. My take is that it’s due to spatial reasoning (most of the challenges are programming that require a lot of shape rotation type thinking), but we don’t know just yet why Gemini is doing so much better.
pietz 2 hours ago
Gemini 3.8 Flash is the most benchmaxxed model to date and even Argon hallucinated so much, it was impossible to use it for any professional work.
fer 2 hours ago
artdigital an hour ago
They’re also excellent (together with Flash-Lite) to use for consumer facing features where speed and cost matters
jbellis an hour ago
https://blog.slopcop.com/a-cheapskates-guide-to-coding-with-...
quibono 17 minutes ago
Intriguing, I might have to try this out - I have an OpenCode Go sub for the deepseeks of the world, and a Claude sub too. Sounds like I could have the best of both worlds here.
timshel2 2 hours ago
hnav 2 hours ago
bcmyguest 2 hours ago
zomiaen 2 hours ago
rozap an hour ago
2III7 an hour ago
cloverich 5 hours ago
Is this now how e.g. Opus works now? I use Opus 5.5 on high for just about everything now, and my bill's not gone up (gone down actually). I had assumed under the hood it was doing this (e.g. I'm sure its not literally Opus doing the log checking / file searches). Towards Google's choice, I'm skeptical introducing a new concept (Orchestrator) for this is really necessary, when they could have just done it by default, unless its plainly lower quality than pinning Carbon.
gnabgib 5 hours ago
thehamkercat 5 hours ago
gnabgib 24 minutes ago
jonplackett 4 hours ago
winstonp 4 hours ago
ainch 4 hours ago
cuvinny 4 hours ago
tonyhart7 3 hours ago
they are same base model
ainch 2 hours ago
Jtarii 3 hours ago
JacobAsmuth 3 hours ago
Ignore all other models.
stopsayingsorry 4 hours ago
Luna, means "moon", smallest.
Terra, means "earth", bigger than the moon.
Sol, means "sun", the biggest object in the solar system.
Astra, plural of the word "astrum" which means "star".
Anyone who gets confused should be embarrassed.
pests 3 hours ago
stopsayingsorry 3 hours ago
LLM's really destroyed the average person's ability to read and comprehend text.
sirk390 3 hours ago
wellnowudontsay 2 hours ago
The only models worth _my_ time are Σεληνη, Γη, Ἡλιος and Αστρα.
I don’t know what to tell you illiterate heretics other than you should know you are bad people. You should be ashamed of yourselves.
The truly αμεταπειστοι among us, the people _I_ hang out with, know these things by their proper name. Which is to say, naturally, 𒌗 and 𒆠 or, if you were even somewhat educated: 𓇹, 𓇾 and 𓇳 (praise be to Ra, the Great Unborn).
It saddens me to see HN has fallen to this level.
throwaway173738 an hour ago
mtlmtlmtlmtl 2 hours ago
I mean, this is what numbers are for. And not only do numbers indicate ordering(without having to do a mapping through severely atrophied school science class knowledge from decades ago), they can also convey meaningful size information using the wonderful technology of units of measurement.
Yizahi 2 hours ago
hoppp 2 hours ago
threecheese 4 hours ago
0gs 4 hours ago
smcameron 2 hours ago
Also 3.8 flash is still visible for me (contrary to what a previous poster experienced.)
I have the "Google AI Pro" plan.
anderber 2 hours ago
trvz 2 hours ago
speckx 2 hours ago
egeozcan 4 hours ago
ps. it's freaking not
flats 4 hours ago
0gs 4 hours ago
NeuraCryption 4 hours ago
acoster 4 hours ago
pmarreck 4 hours ago
small_model 4 hours ago
konart 4 hours ago