agentastic
Nemotron on the other hand is a hybrid (Transformer + Mamba-2) so it will be more challenging to compile it on Cerebras/Groq chips.
(Me thinks Nvidia is purposefully picking architecture+FP4 that is easy to ship on Nvidia chips, but harder for TPU or Cerebras/Groq to deploy)
cathedral = sandbox env in the provider's cloud, so [codex](https://chatgpt.com/codex) uses this model. Their codex-cli product is the Bazaar model, where you run in your computer, in your own environment.
Claude Code, on the other hand, doesn't have the cloud-based sandboxing product, you have to run in on your computer, so the bazaar model. You can also run in in a way that anthropic never envisioned (e.g. give it control to your house). Curser also follows the same model, albeit they have been trying to get into the cathedral model by using the background agent (as someone also pointed out below). Presumably not to lose the market share to codex/jules/etc.
There used to be this thesis in software of [Cathedral vs Bazaar](https://en.wikipedia.org/wiki/The_Cathedral_and_the_Bazaar), the modern version of it is you either 1) build your own cathedral, and you bring the user to your house. It is a more controlled environment, deployment is easier, but also the upside is more limited and also shows the model can't perform out-of-distribution. OpenAI has taken this approach for all of its agentic offering, whether ChatGPT Agent or Codex.
2) the alternative is Bazaar, where you bring the agent to the user, and let it interact with 1000 different apps/things/variables in their environment. It is 100x more difficult to pull this off, and you need better model that are more adaptable. But payoff is higher. The issues that you raised (env setup/config/etc) are temporary and fixable.
For $200plan, it has 40M token cap per day, so assuming the API pricing, the max usage per day is $12/day or 360 per month. (Assuming user max-out usage every day or doesn't hit the 1000message limit first)
relatively standard subscription pricing vs API pricing, i believe they are making money from this and counting on people compare this to Claude Code, which is a much more generous offer.
Any plan/ETA on launching it's big-brother (Qwen3-code)?