Yet it took Codex 8 months to get subagents after their introduction in claude code. This of course pales in comparison to having to symlink CLAUDE.MD to AGENTS.MD
It seems like you’re so close but yet so far. It’s interesting that you concluded that Claude makes it easier to run tasks locally but did not conclude that claude makes it easier to use the cluster. Feels we’re in need of a part 2 where you use CC to automate all of the mundane cluster work.
Also just a hot tip, if you’re able to keep any always-only PC on a university subnet (your PI should have some form of a server) you can use tailscale as a jump proxy and bypass the whole VPN dance.
> if you’re able to keep any always-only PC on a university subnet (your PI should have some form of a server) you can use tailscale as a jump proxy and bypass the whole VPN dance.
This is an excellent way to have yr. campus infosec ppl shut the network port on said server, and then take the hardware to get its OS install scrutinized, and get your accounts locked in the process.
Universities use all kinds of hard to setup stuff which are often custom built. Slurm configs, custom configured HPC servers etc. All of this pays off though if you need to do heavy computations which a local machine won't do.
IMO it would be better to make Claude build out something that makes interacting with the HPC much easier. A web UI, Tailscale whatever.
Yeah train wifi is generally terrible. Basically the only real solution is 100% 5G coverage along all train tracks or starlink. This is basically a global issue because line-of-sight for trains is a hard problem.
16 hours ago the readme for codex CLI was updated. Now codex cli supports openai login like claude does, no API credits.
From the readme:
After you run codex select Sign in with ChatGPT. You'll need a Plus, Pro, or Team ChatGPT account, and will get access to our latest models, including gpt-5, at no extra cost to your plan. (Enterprise is coming soon.)
Important: If you've used the Codex CLI before, you'll need to follow these steps to migrate from usage-based billing with your API key:
Update the CLI with codex update and ensure codex --version is greater than 0.13
Ensure that there is no OPENAI_API_KEY environment variable set. (Check that env | grep 'OPENAI_API_KEY' returns empty)
Run codex login again
But that filter is at best inaccurate then isnt it? Surely there exists a driver which would accept a tipless delivery, but you cannot find them because all you can do is decline to do business.
Americans need to remove the idea of tipping. It's archaic, because it was originally there for an aristocratic/wealthy patron to show off their status to the lowly servants of an establishment.
Just charge a price, and have it include the full service fee required for providing the service.
> You’re not paying for a service, you’re bidding in an open market.
IMHO, this isn't a new phenomenon. Close to 18 years ago, I lived in a city with a popular pizza spot that was about a 10 minute walk away. Normally I'd walk, but having a newborn make that challenging, so I'd get delivery.
Typically, the delivery would take 60+ minutes on a busy night, but after a few consecutive Fridays of a decent tip for the order, the pizza would arrive "burn your fingers" in about 20 minutes.
All that this does is ensure you don't get stacked with another order ahead of you (so the delivery is direct from the restaurant to the person who ordered) in theory.
It doesn't help with situations where drivers are multi-apping (accepting orders across multiple apps and juggling them). The drivers don't even know you have priority.
edit: and in the US where you can definitely see the tip up front, you will almost always find that the order will get picked up quicker if you increase the tip by the equivalent of the priority fee. But you may well get stuck with a delivery before yours.
Doesn’t affect anything in my country using the same apps. I’ve always gotten fast delivery, as does everyone I know and nobody tips. Tipping is for yanks.
this feels weird to me because i always thought i already paid for the service as part of my order. having to go into a open, blind bidding war with other customers to gett my order processed ...
Yeah but most fall apart at lower context than advertised. They do great at simple stuff like needle in a haystack tests but totally flop when you actually try and use that context for something productive.
reply