nebben64

reminds me of Cloudflare OS: https://blog.cloudflare.com/cloudflare-os/

Responding late but just want to say that at my company there are people who think OAI will go out of business one day and maybe some code will be written by hand and/or we'll return to writing code by hand. This person has 'Manager' status btw. fml

just commented ton Tibo's post; they should have made things clearer and told us if the macOS ChatGPT app was going away. So I could either delete it or not be surprised when it rolls into something else :(

Thank you!

wait, you can use other models with CC harness?

hey Boris, with multi-agent work, e.g. Agent Teams, following other agents is not possible because they work so fast. (my tmux panes are just matrix)

do you think something like a /speed config can be introduced to adjust agent working speed and let people adjust?

How is this different, or how does it complement Agent Teams? When should I use which?

> "you are out of tokens" notices

there's your answer. You're likely a heavy user. It's just that in this particular case Auto is shuffling models & reasoning efforts just right so you stay afloat.

There are a lot caveats when people say they're running out credits in hours: lots of people runnings clawS (multiple) 24/7; lots of people using Agent Teams or similar; lots of people just max reasoning for everything; etc.

If you get your work done in the 20 plan, thank the credit Gods and sleep easy. Price hikes are probably coming, or just reasons to draw more credits out from you in one form or another (e.g. new OAI device draws from you 20 sub to use)

My main driver has been Ghostty but I've been looking at Warp for a while. Warp seems like a full on IDE (~ADE) though, as opposed to a minimalistic terminal. Can anyone add some thoughts? Are these 2 very different?

tangential: I've seen Mitchel tweet that people in SF have ran up to him showing him how they fully riced their Ghostty setup. How many people here have done this and how easy/manageable is it? e.g. just forking the repo and implementing whatever Warp feature I like?

I'm 6 days late but if anyone reads this: what does it mean we should "upgrade now to quantum-resistant cryptography" ? If I'm using RSA am I supposed to switch to something else?

I was reading through CC MCPs docs ... MCP Notifications kind of did this right? The server/client could update each other automatically. So there was already this channel-like communication.

This is like that but instead of the server/client sending messages it's you.

people who use pi: is this stuff easy? do I just clone the repo and give SKILL.md arguments to implement features & customize ??

2 days late to this post so not sure anyone's here, but what fascinates me is finding out how the different segments (or other such insects) are connected. Like, at each of those junctions it seems like a bottle-neck scenario where everything has to be condensed into some "wire" form to then connect to the next segment.

Very useful breakdown; thank you!

so are people pairing OpenRouter with open agent harnesses like Pi or OpenCode?

Thanks for the tip. Other ppl are saying "most of us started out like this" but if you haven't played with tailscale etc. (like me). Then this is new and good for learning imo

launch post: https://x.com/joon_s_pk/status/2022023097017421874?s=46&t=by...

You can't write code in the Codex App, it's not an editor. You just manage agents (and ask them to write/implement whatever)

Semi related: what are your guys workflow to PCB design? I need to build an AFE + BLE MCU for a BCI, and having no EE background, my workflow is KiCAD -> buy components -> breadboard testing -> done?? -> order fully manufactured PCB?

I know nothing...

+1 on context window remaining

better memory management: I have memories that get overlooked or forgotten (even though I can see them in the archive), then when I try to remind chatGPT, it creates a new memory; also updating a memory often just creates a new one. I can kind of tell that Chat is trying hard to reference past memories, so I try to not have too many, and make each memory contain only precise information.

Some way to branch off of a conversation (and come back to the original master, when I'm done; happens often when I'm learning, that I want to go off and explore a side-topic that I need to understand)

I think a decent amount of people don't even realize what is happening. For example, lots of people still don't know about the iCloud backdoor that's trying to be implemented by the government.

Those who know are annoyed but not enough that it will cause change; I don't think most believe it will get worse either.

Unfortunately the default will be people going on the App Store, getting the first app that has 'VPN' in the title, download, and forget. Completely failing to address a systemic issue.

how?

how would that work? Besides blocking the websites to download some VPN. Or if someone already has a VPN installed.

Having tried prototypes at neuroscience conferences where their team attended, I can tell you that the device was incredibly brittle (e.g. damp wrist, interference from even the metal table or a nearby computer).

As it says in the article, the device seems to be more robust, and ready for the market soon. After having used ML to tune the decoding model on many participants contributing EMG data.

not sure if OP will see this, but how does uv or uvx forgo `git clone` ? You still need to clone whatever you're trying to run, or am I missing something.

I like your take. Agree that we should label something as 'alive' when there are active biological processes happening; and 'dead' in the absence of any. Also, just get rid of the idea that you're not allowed to move between the 2 extremes; or even that you can't be on some spectrum between these 2 states; (e.g. zombies)

I think "best" is slightly subjective / user. But I understand your gripe. I think the only way is using them iteratively, settling on the one that best fits you / your use-case, whilst reading other peoples' experiences and getting a general vibe

a very clear analysis, that's also very well written

interesting, thank you for the extra info