Path towards spiritual hacking. Ai enthusiast. Just vibe coding SaaS apps and burning tokens. Building tools and educating young minds how to use Ai to build…
Joined May 2016
- Tweets359
- Following189
- Followers73
- Likes185
Pinned Tweet
your loop grades its own work. that's the bug.
part two: the three roles, the contract, and why the evaluator never sees the builder's reasoning.
CodeClawd retweeted
AGI is on the way 🎶🎶
Elon, Jensen, Zuck, Sam and Dario in a hangar singing “I Want It That Way” but every line is about AGI being on the way 🤣🤣
Thanks for sharing. I don’t know if they will implement it or not. Definitely worth it. I will be using it for sure
CodeClawd retweeted
After all the waiting all the rumors Opus 5.5 is here its like they were waiting to use this to beat out the competition I wonder who that could be cough cough grok 4.7 cough
Anthropic is now slowly hard coding the fact that it doesn't want Opus to show its reasoning traces no matter what this is a screenshot from the "Getting the most out of Opus 5.5 Guide" @ClaudeDevs released. The guide is genuinely helpful its when you look closely. you find these "tips"
If every AI API went dark tomorrow, most people vibe coding right now would stop shipping. Not because they can't code. Because they've never run the loop without it.
I spent god knows how much last week across three machines. Those same machines run local models, local transcription and a local voice assistant, and they keep working when the bill or the uptime stops making sense. So why am I still paying for it?
Depending on a tool is fine. Depending on a tool you've never once worked without has a massive potential to becoming something akin to an addiction.
Run one day a month without it. You'll find out fast which parts of your stack are yours. It will make you discover how much reliant we are one frontier AI.
No more driving around town to do house tours.
🚨 SOMEONE JUST KILLED THE REAL ESTATE INDUSTRY
A guy scanned an entire house with his phone. Uploaded it.
Now anyone on Earth can walk through it in a browser tab. No app. No VR. No agent. No appointment.
Click → you’re inside. Every room. Every angle. Every shadow. Photoreal.
The numbers are insane:
- Agent fee on a $500k home: $15,000
- Cost to make this scan: ~$200
- Time to “tour” 50 houses: one evening
- File size: smaller than a TikTok
The science is wild too:
It’s called 3D Gaussian Splatting instead of polygons (how games render), it uses millions of tiny glowing “splats” of color and depth.
AI reconstructs reality from your photos. The result loads on a phone and looks like you’re THERE.
The grift opportunity is even wilder:
Freelancers are already charging $300–$800 per scan for realtors, Airbnbs, venues, car dealers, museums.
One person + one phone + one weekend = a business.
100% Open source. Built on PlayCanvas.
Thank you guys for 50 followers ♥️. Hopefully we can turn this into a community one day that brings everyone including developers, traders, tech enthusiast and people who are willing to learn.
CodeClawd retweeted
I am pleased to see that Ant’s new Claude Code has a version of background computer use on par with the version from Codex from last May this year. Nice work!
Shipping great features first turns out to be a great way to encourage other labs to ship too. We will continue to do this until other labs pay more attention to shipping. This is good for everyone and there is a lot of room left to go!
We solved computer use in practice for GPT models about four months ago. But computer use is a significantly awesome thing no matter what model you use, and it is important that the industry similarly spends more effort to train their models to be great at computer use, among other elements of model capabilities.
As models become more capable and central to businesses and economies, the value of computer use only increases. We should be taking it seriously, and doing the right thing for our customers and the world.
After using Astra and Fable 5.1 for the past week I have come to a find a weakness that both models have. When designing a front-end from scratch both models are creative in their own rights but as soon as it comes to re-iterating and redesigning an existing UI both models fail miserably and waste millions of tokens.