euazOn

I highly encourage anyone e.g. on MacOS to get a cheap laptop and give Omarchy a try. My feeling of using this system compared to MacOS is a whole another level. And now one of the promises of Omarchy Quattro is that AI agents will help you tweak it to your liking very easily, avoiding having to spend dozens of hours ricing your system.

That is actually insane. In my opinion, the future is local AI: for most daily tasks, you absolutely don't need Fable level intelligence - you need Fable level agentic capabilities. And this model has (almost) just that. If we get a similarly capable MoE model in a few months (yes we will), it's going to be an utterly wild ride.

The multimodal abilities are great, but if you deal with text only, what is the benefit of using this over DS V4 Flash/Pro? 13-26x cheaper with comparable intelligence, and available across many different inference providers.

I fail to see the usecase where DS V4 Pro is not enough, but Flash 3.7 is - except multimodal.

Luna is similar, and also 8x cheaper. Source: artificialanalysis

The only benefit I can see is the speed, that looks to be outstanding, probably thanks to their TPUs.

Good points. Speaking from experience, it’s really hard to make it more economical than using a cloud AI service - even if you utilize the GPU to its fullest. There are, of course, other benefits, such as privacy/control/compliance/security, which should be the real reasons to do this, not cost.

Definitely, of course. But I think the logic of the author’s article is based on there being a huge difference between the two, or rather a high cost of inference in absolute terms. And that can change and we have seen it change. Which breaks the entire premise of the article going forward, no?

Inference will be always more expensive than db operations or copying, sure. But how much more expensive is the question.

> If you buy your own GPU, rack it, and run an open model, there is no unit cost.

No. There is economic opportunity cost (borrowing), energy cost, infra cost, depreciation / risk of failure with each unit of work, bandwidth, maintenance, and lots more. Small, but not zero, and often overlooked - especially the opportunity cost.

Exactly my point in another comment. Just to illustrate this further: a rough ballpark of how the cost of intelligence fell since 2022 could be about 1000x, and continues to fall. Unfortunately, it’s really hard to measure.

It’s so cheap that companies choose to spend more on AI inference (more reasoning, more capabilities, longer context), not less - see Jevons paradox.

Yeah, my point is that LLMs can reach that point too. Especially if you do it clientside. Copying was also way more expensive back in the 60s (accounting just for machine time and electricity, not storage cost, about 100 million times more expensive than today). Everything has a cost.

> Meeting that expectation means making LLM calls, and LLM calls cost money.

Of course, and so does everything in the software world. The point is getting the cost so low that it’s basically free. The new DS V4 Flash or the smaller Qwen3.6 models are still really expensive compared to what we were used to in the economics of software, but it’s not unreasonable to expect these costs to continue falling down.

Rough chatgpt estimate says 3-5 orders of magnitude of difference compared to a typical user interaction with a SPA (db/cache lookup, CDN…)

Per Artificial Analysis:

- Haiku: 30 points

- Luna Medium/High/Xhigh/Max: 38/46/49/51 points

That's a massive difference:

- 30 points is Gemma 4 31B territory

- 50 points is GLM-5.2 (744B) territory.

This is more terrible PR for Anthropic.

Reminds me of Slavoj Zizek’s classic example of synthetic sex (look it up), or his grievances about today’s academia: paper written by ChatGPT, peer reviewed by ChatGPT, and consumed by users as a synthesis from ChatGPT.

Don't confuse revenue with earnings.

Coverage and build guide at Linus Tech Tips: https://www.youtube.com/watch?v=eNb55ZwnCRc

I don't know. If this is a real thing, then I'm really sorry for what happened to you.

But this whole post seems a bit fishy to me. Brand new account, and it starts with "Title:" and "Post:", the whole thing being obviously entirely AI generated, and a few other signs.

I am also baffled at how long this vulnerability was left open, but I’m glad you’re at least making changes to hopefully avoid such mistakes in the future.

Just a thought, have you tried any way to triage these reported issues via LLMs, or constantly running an LLM to check the codebase for gaping security holes? Would that be in any way useful?

Anyway, thanks for your work on opencode and good luck.

Ah yes, the classic Apple move of hiding basic functionality behind obscure shortcuts. Thanks for the tip.

In case you're using OpenRouter, check out their new Response Healing feature that claims to solve exactly this issue.

https://openrouter.ai/announcements/response-healing-reduce-...

Try changing the system prompt or switch to opencode [0] - they allegedly reverse engineered Claude Code, and so the performance you get with Claude models should be very similar to Claude Code.

[0] https://github.com/sst/opencode

Is this AI?

I call BS on that. I can get the entire text of the article by just viewing the source, no email address needed. Even if it was somehow needed, it's trivial for a scraper to circumvent that.

FYI, they (oddly enough) communicate mostly through Discord, and they have said they are investigating the issue at 10:30am UTC - 13 minutes after the first user reports.

Could that be due to contractual clauses for uptime in SLAs?

Can somebody brief me on what's people's incentive of posting AI slop on HN? What are they gaining here?

Yep, Stable Diffusion & ControlNet can make for great QR codes. There are even a few dedicated models for it https://qrdiffusion.com/blog/controlnet-models-for-qr-codes

The Karpathy tweet came out 2025-02-02. https://x.com/karpathy/status/1886192184808149383

Nope, not really for voice memos - those are locked away in the app. Unrelated, but it also has terrible built-in support for playing audio files from the file browser.