Hacker Newsnew | past | comments | ask | show | jobs | submit | zackify's commentslogin

I'm one of these unlucky owners. I can't believe I'll ever get anything.

After paying the full cost and being stuck on old software that had a promise of having the hardware required for it


How much does it bother you that despite your vehicle [most likely] shipping with active lidar, the Tesla executiveteam decided to not write software for its modern usage? More or less than the decade of "available next year"s?

Same here. I would totally be fine if HW3 FSD was reduced to $50 a month, but charging the same $100 as HW4 is insulting at this point.

always inside claude code, just using ollama, takes 2 seconds

I'd rather have them in 1password because I use too many different computers and it is perfect for that and with ssh agent forwarding

Anything pkcs#11 you can proxy. I'm using that on some systems - I have an old notebook with a nitrokey hsm at home. It binds pkcs11-proxy to a local wireguard interface, so I'm registering systems I want to be able to use those keys to that notebooks wireguard. They still need a pin for unlocking a session as well.

This is a funny cat and mouse game. They offer a built in loop command.

Just tmux and use that.

Soon if they drop -p people will just vibe code in 5 minutes a way to type inside it remotely similar to their own built in remote access tool. Seems like a losing game from anthropics side


not op either, github actions, self hosted runner on bare metal with lxc containers for each runner.

Cost savings are insane and the speed of latest amd epycs are miles ahead of the default ci instances on github and other places.


Are your self-hosted runner on premise or are you using a cloud service for it?

interesting that was what i thought this was, it keeps boggling my mind the sums being paid for what really could be built by experienced devs on their own teams

You don't want a 40-men strong team that needs to be managed, you want 2 guys that already did it and are hungry for the next 10 problems all on their own.

"Hey guys, make our agents verify tool use before responding to the user. See you in 2 months. Here's 2$b"


Short term: they don’t need devs to build it, it’s already built

Long term: they now have experienced dev(s?) to build their next products and features


I agree that is the reality of why this has happened, but it is completely at odds with the story that that AI maximalists are telling the world, which is that software development is over because LLMs can do anything with a couple of specs and a Ralph Wiggum loop.

Eh, we’re approaching that world (I am "an AI maximalist", I guess)

But someone with the knowledge to guide an AI will have more success than someone without, at least today. I don’t think that will necessarily be true in a year or two.


yeah super confused, it looks like some tools to manage vms in ci? what is unique about that vs lxc or docker or apple's native container cli?

“what’s the advantage of kubernetes over docker?”

orchestration

docker / virtualization framework is for one machine

this stuff is for 100s - 1000s machines


I strongly believe all of these projects are unnecessary.

Install LXC on a server Start a container called dev

Add 25 lines to your zshrc

I say dev1 and it spins up fresh

Dev2 copies from that and is a fresh container.

Auto uses tmux.

Claude code with bypass mode. Do anything. Close laptop. Come back later.

Even have a lock mode blocking all internet access except to the llm provider.

Ssh key agent forwarding through 1pw CLI so it can't even push to github unless I reconnect.

I feel like the Dropbox quote years ago but its a lot easier than people think, and its weird to delegate to another service something that a dev should already understand how to do.

All I have to do to have the same issue to PR flow is open dev1. Open Claude. Have GH CLI and task system MCP.

Do /loop watch for new ticket assigned to me and complete it and push it up.


We see developers build their own setup over SSH with success, so in that sense I agree with you.

However, once you want to trigger tasks from Slack, Linear, or GitHub issues or onboard teammates who aren't comfortable wiring up LXC + tmux + agent forwarding, a managed layer is needed.

I think we're at a moment where builders with great setups like yours and products like ours are feeding each other good ideas. The patterns you figure out in your zshrc inform what we productize, and the workflows we ship give you new things to try. It's a virtuous circle. Everyone should use the right-sized solution for their situation.


Millions of people using Claude code couldn’t write hello world in the language they are using, if they even know what it is.

I am anecdotally aware of at least one project where the author can’t recall off the top of his head what the stack is.


Can you try out cosyra, the whole point is you click and go and so everything your normally would on your desk.

same, even have kokoro for speech back to text for home assistant and parakeet on mac os through voice ink.

Also vibe coded a way to use parakeet from the same parakeet piper server on my grapheneos phone https://zach.codes/p/vibe-coding-a-wispr-clone-in-20-minutes


i am, working great for a long time now

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: