ALT retweeted
this is exactly what i'm talking about
nonsense
It is becoming f*cking dangerous
A 23-year-old dev from China just ran 300 Claude Code agents in parallel and hooked them to a verification layer so none of them could bullshit him
He opens the live dashboard:
- 300 agents writing and checking at the same time
- Every output verified against the source in ~100 ms
- Three passes over 100 company profiles → zero errors left
- Everything dumped straight into an Obsidian vault
The trick is the split: one model does the work, a cheaper one decides if the claim is actually true. The loop doesn’t stop until everything checks out
An analyst team would bill weeks for this. He got it in one run
Same kind of Second Brain + swarm setup that keeps circulating. Bookmark the full breakdown
ALT retweeted
Lots of yapping online about AI vibe nerds making open source alternatives to Adobe Photoshop. Goobers are saying Adobe is finished
My Brother in Christ, free and open source alternatives have existed for decades. Where have you been?
Yeah the guy is braindead. He's showing the most typical, sloppiest AI prose, saying it's 'an entirely different flavor'
ALT retweeted
This is going to upset a lot of Linux users because Linus Torvalds is becoming a fan of AI for programming.
“A lot of people make fun of vibe coding, but I think it’s a wonderful way to find joy in programming. It makes you feel like you’re doing something relevant. It allows you, as a new programmer, to do things that you would otherwise have a really hard time with.”
ALT retweeted
The only group more insufferable than tech people is anti-tech bluesky users, who have been coming back to X in droves the last few weeks.
And they’re just discovering that the entire world got rich over the last two years while they were busy arguing with each other about politics and AI.
And they’re very, very angry.
An unbelievably stupid trend. It's literally the opposite, those who have never learned to code are getting bombed in fact.
The space of AI attracted a lot of ret*rds, which is extremely unfortunate for such an incredible piece of tech.
Try not to hate the tech, hate the people.
People are praising Theo for telling them how he obliterates his Claude Code usage, i.e. how he chronically vibe codes.
This video by @theo gave me superpowers.
I genuinely can’t believe he is giving away all that for free.
I revived an old MBA with Omarchy+Tailscale installed and I’m flying using it as a remote machine.
youtu.be/D8PikZ1KhUo?si=cmNO…
An admission of how good LLMs have gotten. From "it's only good at prototyping" to "I'll only use it if it runs on my GPU"
I agree with him though. It highly depends on the context, but in the grand scheme of things, I agree with him.
My position, which has been the same since the beginning, is: I will never pay for a subscription service to program (nor rely on some Internet service), and I will never turn my brain off and stop caring about the details I care about today.
I am not inherently attached to typing every character, and I think the idea of human language processing and accelerating the production of programming language semantics is exciting. I would only ever do this using local models on my own hardware, and I would employ such tools very carefully (likely using them in my own tooling), and likely not in the ways that many people are employing them today.
If I can accomplish the same work I would’ve been doing by hand more quickly, that’s pure win. But if I accelerate yet lose attention to detail, or the ability to think through those details, that’s not the same work anymore, and so there is some loss. That loss is potentially very important.
Agreed. But I find it genuinely mind-baffling that people who don't use AI are incapable of comprehending that those who do, hate this experience. She's trying to deliver the message to the former, because otherwise the video is senseless, stating the offensively obvious lol
ALT retweeted
Don't use this
Build your own software using their tokens
So when their tokens become too expensive
You can switch to your own GPUs
Your compute. That you control
So you yourself can't be controlled
You need to control your stack -- or you become enslaved
ALT retweeted
Nvidia CEO Jensen Huang on AI model distillation:
“That’s called competition. You’re allowed to test somebody else’s products all you want.”
ALT retweeted
I don't believe you if you say you're passionate about the Software Development Lifecycle
ALT retweeted
Last year, Anthropic was optimizing inference across 3 different types of compute (Nvidia, AWS trainium, Google tpus). There were mistakes made during these optimizations that resulted in actual degradation. Initially Anthropic denied it, but eventually they found, fixed and explained what happened. There have been no notable instances of degradation since.
Sadly, this one instance has made half of tech twitter’s brains fall out.
Separately, there’s the statistics side. You’re more likely to see the stupid spikes over longer windows.
If a model has a 1/50 chance of doing weird shit, and you do 20 prompts a day, there’s a ~30% chance you’ll have encountered weird shit on day 1.
By day 5, it’s closer to a 90% chance 🙃
Tl;dr, people are stupid, don’t understand non-determinism, and it happened once so they feel righteous