Buggy D. Code

I built a perfect clone and improved version of digits.com , Uses @GeminiApp built with @antigravity Fine Tune the Mapping capability with AI on Scanning Different Type of Documents. 100% Mobile Responsive Unlike digits.com Sold for $10K

@ycombinator we made it! Excited to be part of Summer 2026 Batch!

@LexnLin @antigravity we just get tired , as they dont even reply lol... i think 3.1 gemini is not bad... but a better rate for OPus 4.6 should be implemented..

did yall realize how silent all the gemini people have been? what happened with all the accounts like @antigravity must be cooking hard for I/O

@julianweisser Ive been building since i got unemployed lol... no one is stopping me from building ebirforms , its a legacy app used for filing tax here in Philippines used by millions. I've got lot of traction for beta testers. Free Traffic for my paid app called Taxman.

I want to work with you (and invest $100k) if you… 1/ are building solo 2/ feel what you’re building is a calling, not work 3/ have paying customers (or have a good reason you don’t yet / building a moonshot) DM me about the upcoming Solo Founders Program

Yay! My PR on Leptos Wasi is Approved... github.com/leptos-rs/lept… Fun fact I've been using this on goldcoders.dev for server fn I can finally update the dependencies back to official crate

Rebuilt goldcoders.dev using Rust Modular Monolith Architecture With the ff techstacks: Rust , Leptos , Spin , Tailwind , Leptos Wasi , WASM Spin Kube. Scale from zero to millions Anticipating the upcoming traffic for ebirforms.goldcoders.dev

Finally finished all stuff related to our server. Auto Scaling , Hardened Security No downtime deployment Enterprise Grade Server Architecture ... goldcoders.dev

@me256ow just keep building bro... job will always come and go , build something that job cant buy, build your own stuff with rust

I’ve been truly wondering how to go from the mid level rust to senior level rust engineer. How’re y’all closing the gap? I’m genuinely curious. To be honest, job market is brutal and no one wants to hire someone who isn’t a senior rust engineer. I see some mid level roles but well only US/EU specific. No surprise of course. This has been a struggle. There’s no playbook or anything and folks only want to hire someone who they know or staff level. We can blame the market all we want but I don’t think it’s just that.

@windsurf you guys wont let me cancel subscription i never used it why would i pay , now... just add a fucking cancel subscription. And you you Added DONT CANCEL SUBSCRIPTION. WTF IDIOT

i forgot to use @windsurf then after free trial i cant unlink my card , good thing its a debit card otherwise, im getting immediate charge, but you should allow your customer to cancel it...

@LexnLin i take back my word i re subscribe to ultra no choice lol

@buggyDcode yup unless they release some great models and fix agv

yeah okay time to cancel gemini ultra 🙌

@tnm @OpenAI i created waz cli github.com/codeitlikemile…

now hiring for future of devtools at @openai. dms are open.

I've deployed goldcoders.dev and ebirforms.goldcoders.dev to GCP Using Modular Monolith Architecture With the FF Techstacks: Rust, WASM, Leptos Spin, Spin Kube , Kubernets , @stalwartlabs and @resend for sending mail. Probably Overkill LOL #FullstackRust

@AlexFinn its just a storage upgrade lol

It’s happening. 3 months ago I predicted in the next 2 years all hardware costs would triple Base Mac Mini’s would go from $600 to $1,800 Top of the line Mac Studios would go from $10,000 to $30,000 Everyone called me insane. They said it was engagement farming. Yet it’s happening faster than I predicted. I urged you to buy your own compute. I said intelligence will not get cheaper anytime soon. Only more expensive (100% true) Now it’s all playing out in real time It all makes too much sense. As openclaw and personal agents get more popular and powerful, people will need more compute, all while hardware is facing shortages Even the top labs like Anthropic don’t have enough compute to serve models from months ago. Limits going down every week Own your own compute. Host your models. Localize your agents. Do it before having powerful intelligence is reserved only for the elite.

I just need to use OPUS moderately. and Execute all with Gemini 3.1 PRO , so far my only Gripes is the Capacity Reduced on OPUS. Please Increase back OPUS and update to 4.7 for ULTRA Subscribers @antigravity @GoogleAI @GoogleAIStudio @GeminiApp

@GoogleAI @googlecloud what about OPUS 4.7 on ULTRA plan at @antigravity

Our teams have been busyyy! Here are some key updates from the past week: — @GoogleCloud unveiled a suite of AI innovations at our Cloud Next event, including our eighth generation TPUs (TPUt for inference + TPUi for reasoning), Gemini Enterprise Agent Platform, Agentic Data cloud, Workspace Intelligence, and beyond — Gemini Embedding 2, our natively multimodal embedding model, became generally available via the Gemini API and in Gemini Enterprise Agent Platform (the evolution of Vertex AI) — @StitchbyGoogle open-sourced the draft specification for DESIGN.md, so it can be used across any single tool or platform — New autonomous search agents, Deep Research and Deep Research Max, launched to bring MCP support, native visualizations, and unprecedented analytical quality to research workflows across the web or custom sources — Google AI Pro and Ultra subscribers now get increased usage limits and access to Nano Banana Pro and Gemini Pro models in @GoogleAIStudio — @GoogleDeepMind introduced Decoupled DiLoCo, our new resilient and flexible way to train advanced AI models across multiple data centers

@asaio87 yeah unfortunately , as im on ultra plan lol , need to use it but dont wanna renew it

Is there anybody still using Gemini for coding ?

@andyhennie This is nice and useful idea thanks, i will incorporate it to my screenrecorder with computer use , that would be awesome... :D

The secret MacOS API that Codex use for their new impressive computer-use feature. Codex can run several computer-use tasks in parallel, which shouldn't really be possible. Most tools in this space take over your mouse and keyboard completely, so you can't use your machine while they work. Codex doesn't do that. The team at Software Applications Inc. figured out how to avoid it. (That's Sky, by the way, former Shortcuts people Apple acquired a while back.) I wanted to know how they pulled it off. So I did some digging. Here's what I found. The "secret API" is AXUIElement, macOS's accessibility framework. Apple built it for VoiceOver. The Codex team just repurposed it for LLMs. On the reading side: the AX Tree. No screenshots. No OCR. Codex reads the accessibility hierarchy directly. Every button, text field, and menu item is already labeled and structured. It's basically a DOM equivalent that Apple built decades ago for assistive tech. That's what the model actually sees. On the writing side: events go through accessibility APIs, not CGEvent. Clicks hit the target element directly, never through the shared system cursor. Those virtual cursors you see wiggling around? Purely cosmetic. That's why focus doesn't get stolen. That's why N agents can run at the same time without stepping on each other. It doesn't work on Windows, so there they hijack the cursor. The Sky team didn't actually invent this approach. UI Browser was using the same APIs years ago. I found hacks like this super-cool, and hope more people build cool shit with it.

@adahstwt you got no brain lol

USA has ChatGPT USA has Grok USA has Claude USA has Gemini USA has Llama USA has Copilot China has DeepSeek China has Qwen China has Ernie China has GLM China has Kimi China has MiniMax India has?

@GeminiApp @antigravity @GoogleAIStudio @Google FUCK YOU! HAHAHA hope you guys can read this but FUCK YOU