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

surely openvpn being pre-installed on most routers means it's provided to an significant portion?

It is the server that you connect to that is covered by this amendment; they don't care how you connect.

Sure, but openvpn itself doesn't become a "service" just because of that.

i don't think so, it is not provided as a service. if you provide vpn service people can connect to from their router then you need to do age verification before giving them a key/password to connect to the server

brainfuck

I implemented a graph database for my agentic project in postgres. Not top-tier query performance but made an MVP work!


can you share your workflow?


more can lead to smarter in the short term.

brute force


Gemma 3n E4B has been crazy good for me - fine tune running on Google Cloud Run via Ollama, completely avoiding token based pricing at the cost of throughput limitations


What kind of applications are you using it for?


congrats on the first blog post, been using Go+Templ+HTMX when implementing my first startup

I think at least some of these issues can be avoided with a different UI/UX to avoid passing temporal/unsaved data between screens.

looking forward to the next instalment!


Would love to be able to use this UI, connected to an external source like Linear.


community drama aside, great to see more open source agentic CLIs tools.

other than the focus on tui design, does this have any advantage over Claude Code, Aider, Gemini using the same model?


In my experience, Claude Code is scary good. Gemini CLI is just plain dumb and not worth the time.


Gemini CLI in its current state is _dangerous_.

I asked it to examine a codebase and it went lightning-fast into full refactoring mode and started "fixing" stuff - while profusely apologising because it couldn't get the code to compile :D

Currently the best way to use Gemini CLI is to instruct Claude to use it when examining large codebases. Gemini investigates -> generates markdown summary -> Claude uses summary to direct itself without wasting context.


author here

we're very focused on UX and less so on LLM performance. we use all the same system prompts/config as claude code

that said people do observe better performance because of out of the box LSP support - edit tools return errors and the LLM immediately fixes them


  > we're very focused on UX and less so on LLM performance
Could you spin that as an actual advantage? For people like me who use VIM, have a preference about filesystems, and backup phones via adb?


pairing this with Task Master could allow you to draft all of your tasks and effectively have Claude pick something from an endless backlog 24/7...


Doesn’t Taskmaster require an API key? It doesn’t work with a subscription.

You can technically hack the API key from the subscription, but that’s probably brittle.

Or is there some other meta I’m missing?



Nice, thanks!


You need some time to chain tasks. Endless tasks, can't be in random order and there is usually a link between tasks/context.


when I say Task Master[0] I'm referring to specific bit of software that manages task dependencies and ordering.

but I agree, at least the way I use AI tools, it'd be unfeasible to review the code using this method.

[0] https://github.com/eyaltoledano/claude-task-master


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

Search: