dada216

I just had a look at the site and screenshots, I usually run my coding agents containerized (one per project), anyone else doing this and wiring it to herdr? is it possible? from a quick glance it seems to me it installs cc/codex/opencode/etc on it's own and just does multiplexing

I grew up without a father. As it happens children choose father figures when that's the case. Capt. Jean-luc Picard was mine. I can't be the only one who did that, that's how powerful that character was.

I have similar hardware and requirements. Spend the time to write a test process to try multiple quantization configs/multiple inference engine and throw at it a bunch of request you can replay and evaluate the results of. We got it down to a process and everytime there's a new model/options/inference engine version we just run the internal bench/eval suite and make a choice.

I think a small business, even a medium sized one, is better served by either renting proper hardware in a cloud or finding an inference provider to sign a contract with.

Yep, one shotting games, UI in general, is where I found them to be lacking, it tracks with my experience. They do get there with guidance, to me the quality in one shotting things is not relevant though and I don't find I tracking quality on long horizon tasks.

I'm on the Pro as well, haven't checked if argon became available on antigravity, will tomorrow, thanks!

I noticed the usage on chat is absymal, but it could very well be that their own harness does a good job in caching and you can squeeze good usage out of it due to this.

How are you coding on the Pro plan without antigravity? Copy/paste?

Although Argon hasn't delivered on coding yet I think that it's just the first checkpoint of the new model family since Hassabis, and I think it's promising, so if they can get a few good checkpoints in and then price gauge anthropic they can get that sweet sweet coding tools subscription revenue. Antigravity is not that bad, pair it with a good model with good limits, ideally slightly cheaper than the X5/x20 sub from Anthropic, and I, for one, would switch.

I have a pro subscription and got Argon about two weeks after the announcement, I'm on the annual plan, got the 30% discount by switching it from monthly. Usage on antigravity is not included, usage via chat is absymally low. It's a good model though.

What kind of coding/tasks? I find all of the main ones, including the Chinese ones, to be basically on par. Enterprise programming (CRUD all the way down, not simple one though, full ERP)

That is not entirely true. The central committee is extremely powerful, but so are the local governments that actually send the representative, the reason the central committee always votes in unanimity is because the discussion happen at the local government level, a local Chinese government may be ruling over hundreds of millions of people.

I'm not saying this is good, I'm merely stating that the central committee power and Xi's power is still limited by the sheer size of the Chinese state. If you compare that dictatorship to the Stalin dictatorship or Gheddafi dictatorship you'll find that Xi does not have that kind of unfettered power through sheer violence, he still needs to make a high number of cogs to work in unison to exercise it.

And AI is the water

The competitive advantages for US companies will not be left on the ground.

Yes, there is an enormous competitive advantage in using open weight models.

I have setup a sistem where I leverage LLMs and agents to replicate scientific papers, cs and related fields, especially ML ones, and that's what I do in the weekends now.

Are we talking companies here?

Somebody still needs to determine what the company system actually look like, that someone is still probably a programmer, it doesn't matter anymore if that programmer is also a good coder.