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

One window per session

This no good ;)

Old busted screen can do multiple windows per session.


You can run `boo ui` and have all your sessions in one terminal window with tabs, sort of.

The katas container kernel by default.

You can replace Framework with Dell, HP, Lenovo in the title. Why pick on Framework?


More views.


Surprised Anthropic hasn't done anything to restrict Claude Code from using other providers.


At this point in the AI wars, it is probably better to have more users of Claude code rather than restrict which LLMs it can connect to. Claude code is probably (currently at least) stickier than the LLM model itself. Getting people into the Claude code ecosystem is worth it.

Later, they can always lock it down more or add Claude LLM only features to it.


The value of Claude Code the harness isn't that great. There's a lot of other good harnesses out there.


And it gets dragged down by Anthropic actively injecting unhelpful things into prompts without telling users about them (https://github.com/anthropics/claude-code/issues/58262).


I thought so, and then I tried Opencode and Codex and started to appreciate Claude Code a lot more. They've actually done great work with the small details.


I actually have't looked back since trying opencode The ability to properly see what the agent is doing in tool calls and subagents is really unmatched, CC strips all reasoning and return values, only displaying tool calls, and you're unable to expand a single subagent, it's expand everything and scroll endlessly or show everything collapsed with basically no info at all (read x files, ran x commands) Just seems like extremely basic features are missing


What’s your favourite harness? Is there any benchmarks for harness like LLMs have for swe verified?


There Seen to be more and more harness benchmarks out there, pretty interesting read:

https://neuralnoise.com/2026/harness-bench-wip/


You can check my profile for which one I like most :) I do think there have been efforts to benchmark different harnesses.

Personally I'm not going to choose one harness or another based on +/- a few percentage points in a benchmark. I'm going to use one the one that I find the most ergonomic, that isn't too bloated, etc. The models are the primary lever, not the harness.


Good or better? Curious which would be in either bucket.


Probably a matter of taste. I prefer the harness I wrote, I don't want to go near Anthropic's bloated mess of a harness with a 10-meter pole.


IMHO the ergonomics of their tooling are not great. I'd rather use Codex or even OpenCode. Configuration alone is very arcane with lacking documentation. Sandboxing/permission system is quite confusing too.


It went the other way, you can't use other harnesses to connect to the cheaper versions of Claude. So clearly they think their current moat is Claude Code use, not the LLM itself.


The comments about LLM contributed code seems like a specific axe to grind that otherwise detracts from a nice history lesson.

Seems like an interesting fact for those who don't follow the development of vim/neovim.


Do you use x64 emulation with UTM? If so, how's the performance?


No. It's all native Arm. In the UTM app, when creating a new VM, there's an option to say it's going to be "Linux" (generically at that point), which exposes a checkbox which allows you to specify use of Apple Silicon hypervisor.framework, and specifically _not_ x86 emulation.

I use hypervisor.framework, never use x86 emulation, and the result is great. Tested with both Fedora for ARM and Arch for ARM (perhaps CachyOS's bundling of Arch works there, but i did it lower level because i'm an old nerd).


This is what I thought, but idk why the literature about this is never clear that it's ARM Linux only.


which literature? (that question posed, i had to sleuth around to disambiguate oft repeated misinformation before figuring this all out)


I don't have it in front of me, have just seen conflicting info on a lot on articles about virtualization on Mac.

Well wait, UTM's official website clearly says it does support x86 if you're ok with the emu performance hit. Is that wrong?


that checkbox i mentioned above lets you choose to use native Apple ARM via the hypervisor.framework, or use Qemu which lets you do the x86 emulation?


It does support x86 at higher performance costs.


What framework offers all those auth features OOTB?



ASP .NET Core, Ruby on Rails, Django, .... the list goes on and on... The ones that don't usually someone built a package that lets it happen.


I remember Laravel with Socialite [0]. Laravel is what I usually reach for Web SaaS MVP. You only need a VPS and a managed database for testing out the market and can scale a lot without increasing expenses that much..

[0]: https://laravel.com/docs/13.x/socialite


Take this post down immediately ! /jk


Lol, I developed for entrepreneurs who mostly wanted a working proof of concept of their ideas. I guess now you can vibecode them with SaaS for core technical needs.


That's assuming Google can outpace Nvidia, which may or never will. Nvidia is not just going to sleep on it.


Unfortunately, Zed is years behind VSCode in terms of polish, Microsoft supported LSPs just work better in VSCode, they are better integrated, and Zed can't do anything about LSPs memory or peformance.


> Zed is years behind VSCode in terms of polish

One could think that. But VSCode is the one that occasionally failed to simply render text.

No idea what happened these handful of times, but the UI was just completely screwed up, as if it were one of these "scratch to reveal" games, but with the file’s content (and unresponsive, obviously).


I tried VSCode some years ago (immediately moved to Codium) and yes, it is extremely well-done for what it is. But Zed is good enough for me. Everything I care about for Python, TS/JS/CSS and C programming is available. I do not even miss the JetBrains tooling for these.


I'm rooting for Zed but it does feel quite underbaked still right now.


"chat.disableAIFeatures": true


Not sufficient. See the GitHub thread. It is tagging things even when AI features are disabled.


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

Search: