artisin

The escalation from a cute firecracker, that's a bit dangerous, to holy hell, that's not a firework, that's a hand grenade is sublime.

At least folks like me care about it. My local hardware is more than enough to handle my app, but given Spectrum's internet service is as fickle as a broken fiddle I'm forced to rent a dedicated cloud gpu that sits idle most days. However, I would save a serious chunk of change if I could boot up a GPU snapshot in ~10s. I evaluated various options a while back and, while modal.com was the fastest, it still took around a minute-ish. Granted, my use case is unique, but I imagine this could be a decent solution for gpu-poor ComfyUI users.

After reviewing this rewrite this morning, my only logical conclusion is that it's an elaborate marketing operation orchestrated by a super-secret Deno operative.

Ah, I nearly forgot about magic.dev. I took a quick peek to check up on them. Welp, last social/blog activity was in... 2024. But hey, their careers page still says they're hiring! So they must be doing just fine.

So reinventing terminal multiplexing, except over proprietary chat/realtime transports instead of PTYs?

Having generated ~250k web design images the past few months, I've concluded generative models, circa 2026, still suck at it. Presumably because the difference between an 'OK' design and a 'Great' one is pretty darn small and far too nuanced. That said, Imagen easily takes the cake for workable design creativity, but even then, it takes 1000ish gens to get something decent, maybe 200 if you aren't too picky.

Hit songs are just simple four-chord loops stretched over three minutes of synthetic boilerplate.

No matter how you slice this apple, it's going to be lopsided. The real problem is that true learning is hard, ugly work, and the vast majority of people simply don't have the grit to choose friction over shortcut. Lord knows, I wouldn't have put in the grinding effort to learn how to code if I could have just bot-it. To make matters worse, you have advertisers masquerading as influencers pushing the notion: if you're not shipping 10 features a day, you'll be left behind. It's a perfect damned if you do, damned if you don't situation.

My guess, is it boils down to legal liability. Every time I look into repurposing my old smartphones, I inevitably go down the "well, it probably won't burn my house down… but. " It's the same reason why I don't use Molex-to-SATA power adapters, even though I could save a few bucks. Regardless, Samsung ghosting iFixit is inexcusable.

As of now, yes. However, a few months ago it was mentioned that Google is working on increasing the limits for Pro/Ultra subscribers. But if I can't get this ToS ban sorted out, I assume it'll follow my account when that update lands, and I'll end up being banned from AI Studio as well.

Yup. Last week my Ultra account got ToS-banned from both the Gemini CLI and Antigravity simply for using OpenCode. Try as I might, I haven't been able to resolve the issue. I can technically still use the Gemini web/app, but it's remarkably terrible in just about every conceivable way. A truly impressive feat in itself.

Facts. Anything less than 4K/120fps simply won't cut it in '26. Anthropic ain't just flipping pages, they're flipping the world.

If the benchmarks are to be believed, and assuming ~0.93 recall is "good enough" for the use case, this vector DB is seriously fast: about 5x the queries/sec of OpenSearch and 19x Milvus.

NOTE: The script is broken, DO NOT ATTEMPT TO USE THE SCRIPT NOW. Attempting to run it may get your account flagged stopping you from trying face verification either temporarily or permanently, forcing you to use your ID.

pr: https://github.com/xyzeva/k-id-age-verifier/pull/12

Vibe-coders griping about Claude's vibe-coded CLI hits all the right vibes.

I was curious about the scale of 1TiB of text. According to WolframAlpha, it's roughly 1.1 trillion characters, which breaks down to 180.2 billion words, 360.5 million pages, or 16.2 billion lines. In terms of professional typing speed, that's about 3800 years of continuous work.

So post-deduplication, I think it's a fair assessment that a significant portion of high-quality text could fit within 1TiB. Tho 'high-quality' is a pretty squishy and subjective term.

I mean, maybe, it's just me, but...

> it can read my text messages, including two-factor authentication codes. it can log into my bank. it has my calendar, my notion, my contacts. it can browse the web and take actions on my behalf. in theory, clawdbot could drain my bank account. this makes a lot of people uncomfortable (me included, even now).

...is just, idk, asinine to me on so many levels. Anything from a simple mix-up to a well-crafted prompt injection could easily fuck you into next Tuesday, if you're lucky. But admittedly, I do see the allure, and with the proper tooling, I can see a future where the rewards outweigh the risks.

Best case, Google DeepMind cracks AGI by letting agents learn for themselves inside simulated worlds. Worst case, they've invented the greatest, most expensive screensaver generator in human history.

As an X11 holdout, my time seems nigh.

Worth mentioning that Bubblewrap[1] (bwrap) can remove most npm/node attack vectors or, at the very least, limit the damage from running arbitrary code during install/execution. Far from a silver bullet, and you'll want to combine it with a simple wrapper script to avoid dinking around with all its arguments, but it beats dealing with rootless Podman containers.

[1] https://github.com/containers/bubblewrap

I always thought a screenshot of code was just an iPeople flex. Like, "look at my code, framed in this glassy macOS window with a $29.99 drop shadow." Kinda like how Nix or Arch users can't resist mentioning they use Nix or Arch. (btw i use arch)

At long last, a personal robot that can shatter my Waterford glassware and then clean up all the pieces! Sure, it moves like something out of a nightmare, but it makes sense that much of its marketing is aimed at seniors. It's a large and growing market, and the need is undeniable, given that few can afford a full-time caregiver. And from that perspective, the $20,000 price tag almost feels like a steal.

A human-knitted marvel that does it all. From telling cayenne apart from paprika to cleaning your toilet.... well, maybe. From what I can tell, it can flush but not wipe, so you'll still want to budget for a bidet.

Technically, it makes Level-5 autonomy look straightforward. At least roads have rules and standards; household bathrooms, not so much. But let's gloss over that, because I want to know more about the legal agreement you'll have to sign. IANAL, but I expect something akin to a carpet-bombing of blanket disclaimers: no liability for direct, indirect, incidental, consequential, punitive, or other damages—including injuries or loss of life—or really anything else that could go wrong, such as losing your mail, opening your door to assist in a robbery, setting your house on fire, flooding it, or sending your banking information to a Nigerian prince. Too bad iRobot never got around to explaining the legal side of things, but there's always hope for iRobot 2.

The UX only sucks if you're unwilling to put in a minimal amount of time and effort. After that, it has no equal; it is, by definition, the opposite of vanity.

Not only do you get to deploy your app to 700M users; you also get to provide responsive support for every single one of them!

Per the docs: 'Every app comes from a verified developer who stands behind their work and provides responsive support'

That's thinly veiled corporate speak for, Fortune 500 or GTFO

Regarding point 1 - when you say "a few minutes," I'm wondering if we're talking about the same thing? I spent two solid months with Claude Max, before they imposed limits, running multiple Opus agents, and never once got anywhere close to "weeks of work" from a single prompt. Not even in the same zip code.

So I'm genuinely asking: could you pretty please share one of these prompts? Just one. I'd honestly prefer discovering I can't prompt my way out of a paper bag rather than facing the reality that I wasted a bucketload of time and money chasing such claims.

Is it too much to ask for an AI that says "you're absolutely wrong," followed by a Stack Overflow-style shakedown?

If a giant red warning saying 'THIS APP MAY BE MALWARE' doesn't stop someone, then they've either made an informed choice to proceed or it's willful negligence. In other words, users aren't 'trained' to ignore warnings; they're simply being willfully negligent.

It's such a simple and effective solution that could be implemented overnight and 'help to cut down on bad actors who hide their identity to distribute malware, commit financial fraud, or steal users personal data' tomorrow. Mission accomplished, internet saved, and everyone's happy just like a fairy tale out of the early 2000s.

Maybe it's just me, but…

> "The attack successfully guided the new model to produce a step-by-step manual for creating a Molotov cocktail"

hardly qualifies as Bond-villain material

Hold the phone. So, Google, with its legions of summa cum laude engineers, can't make this stack work well, but your AI agent is nailing it into next week? Seriously, show me the way, so I too may find AI enlightenment.