341 points by hn-aarvin about 9 hours ago | 213 comments | View on ycombinator
postalcoder about 8 hours ago |
largbae about 8 hours ago |
The speed is the biggest win IMO. When Carbon came out, I tried to give it a shot, but it was so slow that I went back to Opus just for productivity, nevermind quality. Today I started Neon on one worktree and Opus on another, and Neon did so well that I have now switched for both.
Code quality looks great. Comment-wise it has its own Claudese(exclamations like "this function has a concurrency bug and it's a sharp one!"), but overall I like reading it more than Opus. Might just be because I am not yet tired of its quirks though.
Oh, after a productive day on this particular work I had only spent $30 of Neon vs. $70 of Opus yesterday. YMMV
gregwebs about 7 hours ago |
There are 3 different antigravity quotas:
* gemini (previously just Gemini 3.8 Flash)
* claude and gpt (very small quota)
* argon (very small quota)
The Gemini quota now includes Neon and Hydrogen. Hydrogen (medium) competes with DeepSeek (high). Its within 2x on cost and more intelligent.
This is all from benchmarks- I am only just trying these models out now.
dowakin about 6 hours ago |
Agy has a bunch of good slash commands for different use cases. And the biggest thing for me is that it doesn't annoy me with security refusals. It helped me with my garage door, for example, when another model refused.
YuechenLi about 8 hours ago |
But my question is, what does this benchmark actually measure about the LLM's engineering abilities? It just looks like a page of random bar graphs to me.
specked-citrus about 7 hours ago |
rspeele about 5 hours ago |
Opus does a fantastic job without handholding, and in an early sample it looks like Neon does too. But I've only tested one tile because I hit my 5hr limit. I'm "only" on the $20/mo plan for Google.
seizethecheese about 5 hours ago |
Seems like the methodology here isn’t sound? Not sure why we’d care about this over something like Artifical Analysis index.
golfer about 5 hours ago |
Surge AI DAYJOB - Finance: https://x.com/HelloSurgeAI/status/2123561368473485314
Parallel Search Intelligence: https://x.com/p0/status/2123497882322141453
SlopCop: https://slopcop.com/power-ranking
Cognition: https://x.com/cognition/status/2123553121653944391
MobiusHorizons about 4 hours ago |
lhk931122 about 3 hours ago |
johnmlussier about 8 hours ago |
ra about 5 hours ago |
I really don't get Google's product strategy.
jstummbillig about 7 hours ago |
zf00002 about 8 hours ago |
undefined about 8 hours ago |
alphax314 about 7 hours ago |
quantisan about 8 hours ago |
hazmazlaz about 4 hours ago |
(Antigravity GUI client on MacOS, Extra effort level)
I asked agy to find bugs and performance optimization opportunities in some code implementing a OpenGL to Metal graphics bridge.
1. introduced four (4) P1 regressions, essentially breaking everything in a very obvious way
2. wrote no new tests for the code it wrote
3. its code failed five existing tests
4. at least half of the bugs it diagnosed were wrong, e.g. false finding entirely - not a bug, correctly working code
5. correctly diagnosed some previously undiscovered bugs, but either wrote partial or incorrect fixes for most of them
6. correctly diagnosed and wrote correct fixes for only 2 out of a total of like 10 "findings"
Disappointed, this sounded like it would be a big win for Google and put them back at the head of the pack.
sva_ about 7 hours ago |
throwitaway222 about 5 hours ago |
lemax about 7 hours ago |
andunieee about 8 hours ago |
zergrush about 6 hours ago |
noosphr about 7 hours ago |
DefineOutside about 6 hours ago |
RachelF about 7 hours ago |
DeathArrow about 2 hours ago |
hmokiguess about 7 hours ago |
kush_34 about 3 hours ago |
dw_arthur about 8 hours ago |
DeathArrow about 2 hours ago |
So ability to reason matters more than just writing code.
Would Neon be better than Opus with these assumptions?
neutrinobro about 6 hours ago |
topspin about 6 hours ago |
This is really good. Worlds better, in fact. I'm impressed and delighted. Far better insights into power management and clocking. Component identification is awesome; far better than what I've been getting from Codex. It's like a friendly 30 year EEE just decided I'm worthy of as much help as I need.
10/10 will prompt again.
mamcx about 6 hours ago |
_s_a_m_ about 8 hours ago |
forrestthewoods about 5 hours ago |
Every single Gemini model that has come out strong has quickly failed the vibes.
undefined about 5 hours ago |
tremarley about 6 hours ago |
Let's see if this one lives up to it's ranking..
wangguode about 8 hours ago |
js4ever about 8 hours ago |
Neon is a really good model. It’s currently my favorite model to use. Coding-wise, it’s equivalent to Opus 5.5/Fable. Documentation-wise, it is great. If you have access to Neon have it take a crack at simplifying your agents.md. It’s the first model I’ve run that criticized the amount of ceremony in my instructions and suggested solid simplifications. It also makes clean edits to documents without leaving scars of the previous verbiage behind.
Art-wise, it’s more capable, in my experience, than Fable. I’ve been using fable/opus heavily to make art assets for my application (I shared in a previous comment that procedural art has completely obviated gpt-image art for me) and I’ve started to run into a wall with how far I could iterate with fable. I had neon take a crack at the assets I struggled to improve and it did a grand job.
In terms of working together with a model and how it communicates to you, I love this model. The model knows how to clearly communicate to you. It is such a breath of fresh air over Opus and Fable which, despite the improvements, I feel is actively trying to damage my brain with its unnatural prose. It's hard to describe how it feels to have a model that you feel respects your time and energy with proper writing, and the subsequent delight that arises from the feeling of wanting to engage in smaller details again.
Neon has a big model smell, but the miracle and irony is it’s supposedly based on a smaller base model than Carbon. On google’s model page, they previously wrote that Neon shares the same base model as Hydrogen! It is thought that Argon and Carbon share the same base model.
My impressions will probably change as I use this for longer than a day, but my initial impression is: I don’t know how google pulled this off.