News for hackers. Stuff that matters.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by jbm on Thursday November 19, 2026 @08:55PM (#50569187)
I used it and was shocked at how much better the test tasks I ran it against worked.

I made a little stock gamelet and it came out great vs the same prompt being given to 6.2 sol at ultra.

I think the previous google models were inferior but neon is much better.

That said, I use it via antigravity with a plan so I don't know the cost perspective for someone who is paying per token.

Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by zergrush on Thursday November 19, 2026 @09:38PM (#50569495)
no doubt Neon is a capable model but for us paying $200/month nothing can really match Codex or Claude's usage. Like I have a lot of trouble paying for API to work on a new project, most of the time I am brain storming trying different things until I arrive at a solid direction and putting a meter on it feels prohibitive vs a fixed "all you can eat" plan.

but seeing these subsidized plans are mostly enterprise acquisition schemes I do feel like they will slowly turn into pay as you go type and now that China's access to nvidia gpus is curbed, I think we'll see less and less investment into spending too cheap to meter models as the incentives disappear

All in all I want to say, build whatever you want right now because when there are lot more vibers tomorrow, they won't be able to support subsidized plans. Fact that Google hasn't budged on this tells me that they see no upside

Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by what on Thursday November 19, 2026 @09:51PM (#50569567)
What? You can buy a $200/m subscription from Google too?
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by esafak on Thursday November 19, 2026 @10:26PM (#50569780)
https://gemini.google/subscriptions/

$99.99/ month: 5x higher usage limits vs. AI Pro

$199.99 / month: 20x higher usage limits vs. AI Pro

Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by vintermann on Friday November 20, 2026 @01:38AM (#50570950)
Usage limits in Antigravity, I take it. So you can't take it to your harness of choice, or e.g. run batch image processing jobs. For $200 per month, that's pretty lousy.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by aleqs on Friday November 20, 2026 @01:51AM (#50571039)
Yeah that's pretty shitty. What's not shitty is that you get like 10-20x (maybe more) usage per dollar compared to the anthropic subs. I've been running 3 neon sessions for the last ~hour and I'm still at 0% weekly usage... my anthropic 20x pro sub weekly limit just ran out after about 1 day of semi-active use...

Let's see if this lasts though...

Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by serf on Friday November 20, 2026 @04:29AM (#50572252)
there's always the tried and true "call antigravity from your harness of choice." method if you don't care about opposing the forced bullshit by keeping your money.

imo take your money to someone with the practices you like; sucks when models are corp-exclusive, makes this whole thing tough.

Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by testfrequency on Thursday November 19, 2026 @10:27PM (#50569787)
Which also includes a ton more real-life benefits, not just purely a model (which funny enough, you also get access to other models too).
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by mvid on Thursday November 19, 2026 @10:27PM (#50569788)
Not really. If you want to do anything fancy, you have to pay per token. And that includes using a harness that isn’t google’s
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by kadoban on Thursday November 19, 2026 @11:25PM (#50570155)
Anthropic does that as well, right? Yeah it's pretty ridiculous.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by ImaCake on Thursday November 19, 2026 @11:57PM (#50570343)
Claude subscriptions still work fine in 3rd party harnesses. They tried to remove support but ended up not doing so (yet).
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by kadoban on Friday November 20, 2026 @07:15PM (#50584286)
When I looked a week ago it seemed like if you hook your harness directly to their API you get banned, but you can still do "claude -p" from another harness? I guess? Odd situation. I hope they give up on that sometime, because it doesn't appear to make sense.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by jijji on Thursday November 19, 2026 @11:35PM (#50570225)
you forgot to mention that when you ask antigravity the wrong question, it will ban your whole Google account.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by serf on Friday November 20, 2026 @04:34AM (#50572292)
or the even funnier version of that : an innocuous seeming primary prompt that drives a sub agent into something nefarious by virtue of search radius.

ex: you prompt an llm to assist in forcing a mobile browser into kiosk mode, the llm determines via a fanned out sub-agent that it can only achieve that with a root and it determines the mobile has a locked boot-loader; so it starts considering exploit methods from XDA until the cyber-security leash hits the whole slot.

some variant of this hits me almost every day on oAI begging that I join their project daybreak shit and submit an ID, it'd be a lot scarier against a 25 year old google account.

Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by jxf on Thursday November 19, 2026 @11:51PM (#50570323)
See: LiteLLM.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by noduerme on Friday November 20, 2026 @12:06AM (#50570397)
Maybe someone can help me clear this up: I've got a $20/mo subscription to Claude that's not through a console, and which I just use as a chat/coding window in VSCode. Then I have an API key that I use with OpenClaw in a sandboxed system. Both are using Opus 5.5.

A good 4-6 hour session of code and tool usage on the API can run me $80-$100. Are you saying I can get that all for $200/mo if I switch to Claude Code and use the high end subscription?

Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by computomatic on Friday November 20, 2026 @12:11AM (#50570431)
Yes. My Claude Max 5x sub gives me approx $2,500 worth of tokens per week ($10,000/mo) for $100/mo. I think 20x is roughly double that.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by noduerme on Friday November 20, 2026 @12:37AM (#50570566)
so ... I just have to give up the openclaw harness? I guess my understanding atm is that they'll reject calls to a subscription method if they're coming from a claw.

I wouldn't say my relationship with the claw is worth an extra $500 or something, but there are serious improvements over using Claude Code directly. Scheduled jobs, the whatsapp channel, and a bit of personality... I'm disinclined to hunt around for another harness that Anthropic would accept on the terms of their subscription, only to find it banned shortly thereafter. Is there a well trodden path to just using openclaw on one of those higher level subscriptions instead of raw API pricing?

Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by neuronexmachina on Friday November 20, 2026 @01:17AM (#50570829)
The Max and Ultra personal subscriptions also include an equivalent amount of API credits each month.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by qwerpy on Friday November 20, 2026 @01:17AM (#50570830)
The $100 and $200 Claude plans give you $100 / $200 of API credit per month.

https://platform.claude.com/docs/en/about-claude/api-credits...

So you can get massively subsidized coding use (I use it through T3, herdr works, the official clients work too of course) and also get a modest amount of API credit for whatever you want (claw, etc.).

Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by Koffiepoeder on Friday November 20, 2026 @01:59AM (#50571083)
The grey market may or may not have some solutions for this. Usage is at your own risk.

Theres also options to connect openclaw via the real cli, but that does blow up your system prompt. I use that option right now and it works quite well. There's no free lunch as they say.

Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by radlad on Friday November 20, 2026 @12:31PM (#50578561)
If you're open to switching, Hermes has a method using the Agent SDK that is sub-based: https://hermes-agent.nousresearch.com/marketplace/claude-sub...

I've been using it for a couple months.

Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by Betelbuddy on Friday November 20, 2026 @09:59AM (#50575596)
Enjoy it...It wont last long...
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by aleqs on Friday November 20, 2026 @10:20AM (#50575920)
Claude subs are absolutely terrible value now, and comparing it to anthropic's own API pricing, which nobody actually pays is very misleading. The Google AI sub is like 10-20x the value/usage right now.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by aleqs on Friday November 20, 2026 @10:18AM (#50575890)
Anthropic sub usage has been nerfed like 10x in recent months, it is absolute shit value. I just switched over (rather added) Google AI ultra sub and I'm getting like 10-20x usage that I would get from my anthropic x20 sub.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by aleqs on Friday November 20, 2026 @10:16AM (#50575844)
This is such complete bullshit. Google ultra/pro subs give like 10-20x more usage per $ than anthropic and openai subs.