lemontheme

Think you might have clicked post too fast. Did you mean the

This mirrors my experience.

I'd feel bad calling it 'half-baked' though, seeing as they've published some incredibly in-depth posts about how they develop and test the vim mode. (At the time of writing at least, they had a Neovim core contributor on the team.)

So it does surprise me they haven't made switching between panels more seamless. I've had to add a bunch of extra custom keybinds, and tbh I'm still getting tripped up. Feels like I'm constantly reminding myself to switch between different sets of muscle memory.

Imagine having access to information about thousands of years of human history, with all its big migrations, the ebbs and flows of civilizations, religions and empires, and still actually thinking one people in particular have some natural claim to a stretch of land.

What if instead we respected state sovereignty and international law for the betterment of all instead of continually stirring up shit to benefit of a few powerful figures?

Hm, that rather sounds like terrorism

Just curious – what privileges do you feel you've had to give up on the path to a slightly more equitable society?

Because as a man myself I honestly wouldn't be able to say which privileges I've lost that my forefathers enjoyed, besides sexism with impunity. In fact, I have it easier, for the time being at least. No military conscription for one. And with the recognition that the patriarchy hurts all I've been able to actualize myself in a way that is more authentic to myself than the constraints of past generations would have allowed.

Good. They’re fuel-inefficient, low visibility murder machines that do not belong in Europe, where city roads and parking spaces tend to be narrower. Not once in the last few years have I seen a pickup truck bed in use. Average number of occupants: one, male. And it’s always the same kind of person. Like with cybertruck owners, there’s an air of overcompensation. Where they’re not compensating, unfortunately: road taxes, where they’re taxed as a non-commercial vehicle, despite polluting and weighing as much as a small van, while being driven by some of the least road safety conscious, tailgating assholes I’ve encountered.

(/rant. Pickup trucks have a purpose, such as in low density rural areas. That’s not the case in Belgium, for instance. Either you need a van because it’s for work, or you rent a lightweight van on the few occasions you actually need to transport a lot of stuff.)

Haha true. I’d considered that. But then, so is any code the agent writes, which will ultimately run outside the sandbox.

So it’s certainly not perfect. An isolated VM or a VPS provides the best guarantees. For me though it’s good enough. I’ve put my risk profile at: ‘don’t fuck up my system directly and don’t exfiltrate secrets directly’

Cool! As a professional programmer few things consistently succeed in making me feel inept like trying to build an Apple Shortcut

Lately I've taken to Iosevka, the 'curly' variant to be precise. Even though I hated it when I first tried it, I revisited it because I was noticing that, with coding agents running in the same window, I wanted to be able to see more at a glance. With Iosevka's semi-width glyphs you can just fit a lot more in the same space. Took a day or two to get used to its slender appearance. Now every other font feels unnecessarily w i d e

I really like lima too. It's my go-to recommendation for light VMs. But I do consider it slightly less convenient.

A good example of why is project-local .venv/ directories, which are the default with uv. With Lima, what happens is that macOS package builds get mounted into a Linux system, with potential incompatibility issues. Run uv sync inside the VM and now things are invalid on the macOS side. I wasn't able to find a way to mount the CWD except for certain subdirectories.

Another example is network filtering. Lima (understandably) doesn't offer anything here. You can set up a firewall inside the VM, but there's no guarantee your agent won't find a way to touch those rules. You can set it up outside the VM, but then you're also proxying through a MITM.

So, for the use case of running Claude Code in --dangerously-skip-permissions mode, Lima is more hassle than Nono

Might be something specific to my and my colleagues' systems, but it breaks the TUI. It needs git authentication, which fails, and the TUI stops accepting input reliably

And for the macos users, I can’t recommend nono enough. (Paying it forward, since it was here on HN that I learned about it.)

Good DX, straightforward permissions system, starts up instantly. Just remember to disable CC’s auto-updater if that’s what you’re using. My sandbox ranking: nono > lima > containers.

> But that is not the overarching point.

Because that could be easily resolved by factoring % cache hits into the usage limits.

> Literally everyone does this.

Never a strong justification, much as I like Anthropic in general.

Why is the 'Mercedes gas station' selling gas 85% cheaper but only to Mercedes drivers?

Why is the 'Apple electric company' selling cheaper electricity to households with Apple devices?

They're not the strongest analogies, I'll admit, but that's what it smells like to me.

You're presupposing fraud and illegality. That's what I'm questioning.

That said, some good can come of this in the sense that it will (hopefully) discourage these kind of schemes. They don't create value and they harm smaller competitors, who now need to divert resources to increasingly sophisticated bot detection.

Oh I don't deny what he did is most likely a ToS violation. And under those terms, he should probably be forced to pay back the money.

But I don't see how it's fraud in the criminal sense. That's just my judgement as a citizen, not a lawyer. All I see is the shopping mall shaping criminal law to its own benefit.

As for the military bases, yeah, stay away from those, kids.

Flooding stream services with slop and autoplaying it through a bot farm is obviously bad behavior, but is it illegal, punishable with jail time (5 years mentioned)?

I see no victims other than large streaming services who failed to account for a changing reality.

I’m getting ‘because of torrenting metallica won’t be able to afford its third private jet’ vibes from this

‘abuse’. The same rate limits apply, the requests still go to the same endpoints.

Even as a CC user I’m glad someone is forcing the discussion.

My prediction: within two years ‘model neutrality’ will be a topic of debate. Creating lock-in through discount pricing is anti-competitive. The model provider is the ISP; the tool, the website.

Occupying, expanding, and killing does tend to radicalize your surviving neighbors.

I mourn the innocents on both sides

This is generally how I use it too. Every now and then I click through to the assistant for follow-up questions. I appreciate that it’s there, even if I use it infrequently. The default kimi model gives surprisingly good answers too

At least the thinking trace is visible here. CC has stopped showing it in the latest releases – maybe (speculating) to avoid embarrassing screenshots like OC or to take away a source of inspiration from other harness builders.

I consider it a real loss. When designing commands/skills/rules, it’s become a lot harder to verify whether the model is ‘reasoning’ about them as intended. (Scare quotes because thinking traces are more the model talking to itself, so it is possible to still see disconnects between thinking and assistant response.)

Anyway, please upvote one of the several issues on GH asking for thinking to be reinstated!

First, the difference isn’t that big in the economically stronger EU countries. Second, you need to factor in cost of living, which by most accounts is lower. Third, meaningful labor laws and a shared appreciation for work-life balance. And finally, to continue the sweeping generalizations, while we celebrate business acumen, we don’t fetishize wealth. People who flaunt money get made fun of, as do sigma grindset hustle bros.

I’ll take a pay cut any day for the ethos of the EU.

> Trusted by devs at

  Palantir [...]

Yeah, I'm out.

Should he? Where does that mindset come from? The author has owned up to his mistake. Unless there is a pattern here, why would we not prefer to let him learn and grow from this? We all get to accidentally drop the prod DB once, since that’s what teaches us not to do it again.

Oh nice, this is going in the tool belt. Simple and self-explanatory. Hits the same notes as excalidraw.

Only thing I couldn't figure out right away is how to copy the drawing itself (not the JSON data). Eventually I found cmd+shift+c in the keyboard shortcuts. Bit later I found 'Export Text' by clicking on the project name (default: 'Undefined').

I'd put that functionality a bit more front-and-center

Maybe it's just more or less feature-complete? Was curious, as someone who hadn't heard of it before, so I checked the blog. Last post is from April last year and concerns public testing of a new release. That's not particularly old, if you ask me?

Few games have captured my imagination like CoQ. Only, I wish it wasn’t so punishing. Death lurks around every corner. Even in roleplay mode (with permadeath disabled), you can lose hours of progress if you die between villages.

I understand the appeal. It makes the stakes real. You learn to run away rather than fight. But while it’s fun to laugh at all the ways you’ve died, if you’re a perpetual noob like me, it’s also frustrating. Survival seems to depend on keeping the wiki at hand. I contracted ‘glotrot’, for instance. Didn’t understand how or what I could have done to avoid or how to get rid of it. It was all there in the wiki. Maybe I could have soldiered on until I’d found an in-game book with the right info. Maybe I could have used that info in my next run. But with runs taking tens to hundreds of hours, that’s a big investment!

Still an incredible game though. I think about it more than any game I’ve ever played. The Steam Deck controls are also surprisingly effective for a kbd+mouse game!

The 'a' and the 'o' are a bit similar, but all in all I can see myself trying this out. Reminds me a bit of Comic Code and Maple Mono. Thanks for sharing!

There are a few odd things about this post though. Take this as well-intentioned feedback.

- New account. No previous submissions or comments.

- New Github account. No previous activity.

- Mentions custom engine (cool!), but omits any details.

- Calls other mono fonts 'fugly'; refuses to elaborate.

- Releasing based on interest feels like engagement farming. Let me know when it's done. Then I'll judge whether I'm interested.

- Regular weights are free. Implication is that other weights will be paid. That's fine. I'm happy to pay for fonts. But I'm unlikely to try a font in earnest without bold and italics.

Sorry if this comes off as harsh. I wish you the best with this!

Before this drama started, OpenCode was just another item on a long list of tools I've been meaning to test. I was 100% content with CC (still am, mostly). But it was nice to know that there were alternatives, and that I could try them, maybe even switch to them, without having to base my decision on token pricing. The idea of there being escape hatch made me less concerned about vendor lock-in and encouraged me to a) get my entire team onto CC and b) invest time into building CC's flavor of agents, skills, commands, hooks, etc., as well as setting up a marketplace to distribute them internally.

While Anthropic was within their right to enforce their ToS, the move has changed my perspective. In the language of moats and lock-ins, it all makes sense, sure, but as a potential sign of the shape of things to come, it has hurt my trust in CC as something I want to build on top of.

Yesterday, I finally installed OpenCode and tried it. It feels genuinely more polished, and the results were satisfactory.

So while this is all very anecdotal, here's what Anthropic accomplished:

1) I no longer feel like evangelizing for their tool 2) I installed a competitor and validated it's as good as others are claiming.

Perhaps I'm overly dramatic, but I can't imagine I'm the only one who has responded this way.

Gotta admit, the phrasing tripped me up as well. You underestimated the effort that ultimately went into it

As a European, I always get a giggle from American conservatives describing CNN as ‘far left’. There’s so much more spectrum to explore. Like, even your Democrats are our center-right.