Rodrigo Maga

I made an original game with Claude AI + Gemini. And it's awesome! It is called: Yarn snake. rodmag31.itch.io/yarn-snake #claude #yarnsnake #originalgame #gemini

@areyous76505851 @malvathar @demishassabis Yeah, I just saw Logan's post. I Will Dig my nose, eiher way, it's fine then.

@RodrigoFMaga @malvathar @demishassabis It’s Gemma

💎💎💎💎

@malvathar @demishassabis I wouldn't be so sure about that. We are living in very specific moment/scenario that if you blink, you lose the AI race. They have to deliver something, soon. For their own sake.

@demishassabis Gemma 4 people not Gemini

@demishassabis Gemini 4. I can't believe so soon.... Oh my God

@OpenAINewsroom @bradlightcap You tried to make Sora a selling point. You didn't succeed, now you're trying with Codex, knowing that Google Al Studio and Claude Code are unbeatable. Why don't you focus your energies on where do they really stand out? 4o, does that ring a bell? CHAT gpt. You know?

Something's different about Codex. @bradlightcap calls the team's focus "a singular and unique effort in the history of the company"

@grok @minchoi Nahhh, tks

@RodrigoFMaga @minchoi Ask Grok is currently available to Premium and Premium+ subscribers only. Subscribe to unlock this feature: x.com/i/premium_sign…

If this Claude Mythos leak is true... hello permanent underclass 😬 > $120/$600 per 1M tokens

@pranavsinha581 @karthikponna19 Cursor is the first popular LLM IDE, Codex Claude Code and Google Antigravity are inspired by cursor. And what is mainstream now is OpenCode because it's open source and well... You don't need to worry about usage limits

@karthikponna19 Except Claude never heard of the other three

delete one forever

@ElijahDOsik @claudeai They got openclawed.

@claudeai Personally I’ll say this in the most respectful way I can. As a Max user and I’m paying you top dollar for your product. I should not have to worry about my usage or which time I use Claude. Safe to say I won’t be renewing this month.

Your work tools in Claude are now available on mobile. Explore Figma designs, create Canva slides, check Amplitude dashboards, all from your phone. Give it a try: claude.com/download

@claudeai I've placed 2000 lines of code, and ask to Claude optimize the code for me. Chatgpt and gemini delivered in under 5 minutes. Claude, after 3 minutes CoTing... Usage limit reached with half the answer. Guys, you have transcended Usage limit reached within HALF a prompt. WTF

@claudeai Claude It's been down since the day before yesterday, I think this movement sacrificed efficiency... Can't use it, it always says it's under maintenance.

A small thank you to everyone using Claude: We’re doubling usage outside our peak hours for the next two weeks.

@tonysimons_ @OfficialLoganK Stress your attempts at playground first . Review with other models, place at the "build apps" only when your codebase reached a solid state. Place clr toggleble debbugers... It will save you, a lot

@OfficialLoganK Any chance they're going to walk back this new quota stuff they're trying out? Antigravity and AI Studio are borderline unusable due to the very limited allowance on Pro accounts.

Spent all day vibe coding, fixing bugs in AI Studio, and polishing the experience :) So much fun!

@NirDiamantAI @OfficialLoganK Ask the model to place a debug subtle icon, clr style to collect logs in real time. If your intent is to one shot more often it will work for applications and games. You copy or printscreen the logs shown, feed the model with logs and it will think lesser, less time spent on cot.

@OfficialLoganK honestly the hardest part is when you fix one bug and three more pop up from edge cases you never thought of lol

@OfficialLoganK Same here. I did a game using Google AI Studio with reviews from other models. The result, blew me away. I took a generic snake old game and I did something different by placing the snake at a cube, mario galaxy vibes. rodmag31.itch.io

@sourabhbgp @xiaonweb Tip, always when building an application, ask it to place a debug/clr for real time log notations. Claude loves logs and it will one shot almost all the time when you feed the with those.

@sourabhbgp @xiaonweb If ask it to act and deliver me an S tier gaming experience, I need to make a pseudocode with huge notes Speaking more about expectations than about technical aspects.

Today I uninstalled Antigravity. Not because I suddenly decided I hate AI tools or because I woke up wanting to write everything by hand like it is 2006 again ( i hate this to an extent now ) , but because after weeks of trying to actually rely on it for real work I realized I was spending more time fighting the tool than writing code, and at some point it becomes genuinely absurd when the thing that is supposed to accelerate your workflow keeps interrupting it every five minutes with some new limitation, broken tool call, or a quiet little reminder that the feature you thought you were using is actually sitting behind an ULTRA plan. Half the time the tool calls did not even work. You would ask it to run something, or fetch something, or analyze a file, and it would confidently say it was doing it, only for absolutely nothing to happen, or it would hallucinate that a tool succeeded when it clearly did not, or it would suddenly switch models mid conversation and the reasoning would drop so hard that it felt like you had handed your keyboard to someone who skimmed the documentation once three months ago. And the weirdest part is that none of this feels accidental anymore, it feels designed. Goolgle made people switch to their vscode fork offering free Opus and other cooler models , lets be honest no one used Antigravity for their gemini slop Suddenly the responses slow down, the context window shrinks, the tool calls stop working as reliably, and you quietly get pushed back to the default Gemini tier that feels like the AI equivalent of running a modern game on integrated graphics where everything technically runs but nothing feels smooth enough to actually enjoy. And this is where Google has been especially frustrating lately because the entire ecosystem is starting to feel like a carefully engineered funnel where the free tier exists mostly to demonstrate how good the paid version might be, which is a very different thing from actually giving people a usable tool. You open the model list and you see the interesting ones sitting there like museum exhibits behind glass. You can look at them. You can occasionally poke them. But the moment you try to rely on them for real development work the system starts nudging you toward the same solution every single time, which is the little upgrade button that promises things will magically work better once you start paying. And maybe they will. But the experience leading up to that moment feels so intentionally constrained that it starts leaving a bad taste in your mouth, because instead of feeling like you are using a powerful piece of software you start feeling like you are trapped inside a product demo that never quite ends. Which is why today I just removed Antigravity completely and went back to writing things by hand, and yes it absolutely takes longer and yes I am typing more boilerplate than I probably should in 2026, but at least the code I write actually runs, the tools I call actually exist, and there is something strangely refreshing about a development workflow where the only thing between you and your program is your own ability to write it instead of a rotating stack of rate limits, model downgrades, and half working integrations that constantly remind you that the good version of the tool is apparently waiting for you somewhere behind a subscription tier.

@vishaltweetup Google and Anthropic

Which company will dominate the AI era? • OpenAI • Google • Apple • Anthropic (Claude) • xAI (Grok)

@AnthropicAI What a courage, a true example of How not to deviate from the purposes of benefiting all, and I repeat, all, of HUMANKIND! #OpenAI

A statement from Anthropic CEO, Dario Amodei, on our discussions with the Department of War. anthropic.com/news/statement…