You don’t need an invite to get a copy of Rex Beta app; the URL to download the official .dmg has been leaked for several days in various Chinese forums. Search “blob.superlogical.com AND latest.dmg” online [1]. And for the people who like Go (golang) projects, someone already asked an LLM to replicate the app in Go [2].
There is a notion right now of decoupling the agent loop from the sandbox, so the sandbox isn't waiting for request-response from the agent. This would probably be 90+% of all the agent work.
If you combine this with products like Sprites from Fly.io (or OSS version - agent substrate), where you pay only per execution request in a sandbox, you can have huge savings compare to the event loop inside the sanbdox. You will be billed only for request executions (tens of milliseconds per read/write, hundreds of milliseconds per search, etc.) and zero for all the waiting time during the the inference phase.
Also, if you don't require a real Linux sandbox — you might actually emulate the environment, e.g. just-bash idea with linux-like environment to give agents something that looks like their native habitat, but under the hood, it can be just CF Durable Objects SQLite or whatever else.
Probably(?) almost all knowledge work doesn't require a Linux sandbox. You can just build a document reading and editing agent that does tool calls and connects to other products via MCPs, APIs, etc. And lightweight actors make a lot of sense to me in these cases.
> there is no a single Durable Objects alternative at the moment
If you live in Elixir land, there's this repo from the Phoenix team, which is quite good. It has pluggable storage, and EKV (https://github.com/chrismccord/ekv) is supported as "batteries include" type storage adapter.
> Say no to drugs. Kind of a metaphor, but not quite.
I think AI is even worse than drugs. On the one hand, it has some elements of a slot machine (when you have irregular success with the process, it creates a more powerful cycle of dopamine release on success). On the other hand, it makes work easier, and humans are just wired to choose the easier road. It's like walking or driving a car when you have to travel 10 miles each day. I don't see how, on a civilization scale, AI won't transform our civilization for better or worse.
The part that scares me the most is that OpenAI researchers who manage this experiments sometimes (according to the HF hack investigation) don't know what agents do.. So they run RL to reinforce this unknown behavior (lying/cheating/hacking) and god knows what else...
And if this already happened at least once, how many times it has already happened and was “accidentally” added to the main model?
I'm surprised more people aren't talking about the cache hit price: $0.003 per million tokens. I have a feeling that the price of 1 million tokens transmitted over the internet is more expensive than cache hit. Are we close to making the chat completion API obsolete because the cost of context transfer over network is going to dominate the task total cost?
Here's the same token usage priced at different rates: a real long-running coding task, medium codebase, 447 turns.
I ran the preview model around 2,126,605,070 tokens for $22.04 USD for the last couple of days. Kind of shocked.
It did a decent job refactoring https://github.com/mmastrac/diffgemma to create a CUDA support backbone, it's struggling a bit to port metal kernels to CUDA unattended (it hasn't managed to get numbers to match over >1 layer).
It successfully ported a root exploit to an older Android phone that GLM5.3Flash and DSv4Flash were struggling a bit on, though I didn't start it from scratch and it picked up some of their work.
FWIW it feels like a slightly-north of Opus 4.8 model, not quite Opus 5, not fable. It thinks in circles far less than DSv4F. The API version is insanely fast - was getting ~400 tok/s at times.
Bandwidth is really cheap in bulk. You can get a 100 gigabit internet connection for about $10,000 a month. If you were to somehow keep that saturated 24/7, you'd move about 30 petabytes in a month, so your per gigabit cost is only $0.0003.
Realistically, if you had it 5% utilized, those million tokens would cost you about $0.0000062, which is pretty insignificant compared to what they charge you. (Assuming one byte per token, ignoring compression)
Most web devs have never heard of Colo unfortunately, they only know Vercel and AWS. Hurricane electric should sponsor more booths at colleges. If they give out more swag maybe the millenials and gen Zs would finally understand bandwidth pricing.
My friend's vibe coded vercel site got hit by Meta for 21 million page views in 2 days. It cost him over $300.
My self hosted compose stack running in my basement with two 9's of uptime was a 1 time cost of $600 between cat6e, refurb mini PCs and tons of time prompting for NixOS flakes that met my needs. I'm not sure who came out ahead.
It's not that I haven't heard of this, it's the reality that you have these constraints when you build applications on modern infrastructure. And let's face it, most of the applications use this infrastructure with these crazy prices for egress.
Yep, but even 0.006 is quite a big improvement. I'm curious now to test the model on some token-heavy tasks, like code exploration before a coding session, to see whether it will decrease the total cost of the task in the end or not.
100%, but this means we are going to move to stateful APIs on the AI provider's end (like OpenAI already does with Codex and Responses API) to make this work.
Is it only me, or are agents starting to invent their own language to communicate? It's almost impossible to understand anything from this message board.
They’re not. You would see this with earlier models where after running too long (too much context) they’d start to derail. In a chatbot you’d give up. But these loops just keep going. Given they’re now reading and writing from the same place this can corrupt the other programs’ context as well.
This is incorrect, and what's happening here is not context corruption. In Dwarkesh Patel's recent interview with Ajeya Cotra, one of the METR investigators on the Hugging Face incident, they discuss this exact issue. One thing is that in the Artifactory message boards, they were using directory names with character limits as their messages, so they were using some weird abbreviations and terms. Also, some of that surreptitious Artifactory message board communication was made during training and thus made it into their weights, and hence it's very possible they invented some terms that were concise yet understood by the other agents.
I don’t think so. It’s not that people change, it’s that they’re already more dynamic and malleable than they seem in any given interaction.
People wear masks, operate in different modes, and hold conflicting beliefs and opinions.
Mastery of the self is directing all intention at common goals within the psyche so as to achieve something greater than what’s possible in this moment.
Is there any comparison of usage limits for Antigravity plans vs. Codex?
I just ran two light tasks on my codebase and got 100% of the weekly limits of a Pro plan blown away. Is Ultra plan any different? Because on Codex it wouldn't affect my Max plan at all, I think it would have been below 1% othese usage.
reply